How Should My Chatbot Interact? A Survey on Social Characteristics in Human–Chatbot Interaction Design
Open accessAbstract
Chatbots’ growing popularity has brought new challenges to HCI, having changed the patterns of human interactions with computers. The increasing need to approximate conversational interaction styles raises expectations for chatbots to present social behaviors that are habitual in human–human communication. In this survey, we argue that chatbots should be enriched with social characteristics that cohere with users’ expectations, ultimately avoiding frustration and dissatisfaction. We bring together the literature on disembodied, text-based chatbots to derive a conceptual model of social characteristics for chatbots. We analyzed 56 papers from various domains to understand how social characteristics can benefit human–chatbot interactions and identify the challenges and strategies to designing them. Additionally, we discussed how characteristics may influence one another. Our results provide relevant opportunities to both researchers and designers to advance human–chatbot interactions.
Verified 2026-10-09 · 1 reference not checked yet
AI snapshot
Written from the paper’s full text.
TL;DR
This survey analyzes 56 studies on disembodied, text-based chatbots to derive a conceptual model of 11 social characteristics grouped into conversational intelligence, social intelligence, and personification. It maps reported benefits, challenges, and strategies for each characteristic and proposes 22 interrelationship propositions to guide chatbot design and future research.
Key findings
- The review derived 11 social characteristics: proactivity (18 studies), conscientiousness (11), communicability (6), damage control (12), thoroughness (13), manners (10), moral agency (6), emotional intelligence (14), personalization (11), identity (16), and personality (12).
- These characteristics are grouped into three categories: conversational intelligence, social intelligence, and personification; the paper reports benefits such as increasing human-likeness, believability, engagement, and interpersonal relationships, alongside challenges such as timing, privacy, emotional regulation, and stereotyping.
- The survey states 22 propositions about how characteristics influence one another, e.g., proactivity influences perceived personality and conscientiousness, and identity influences moral agency.
- Most surveyed papers focus on task-oriented chatbots (59%), while general-purpose chatbots account for 33%; education is the most representative specific domain with 9 papers, followed by customer services with 5 papers.
Methods
- Literature survey using Google Scholar with a search string covering synonyms such as chatbots, chatterbots, conversational agents, conversational interfaces, dialogue systems, and digital assistants; studies on embodiment, speech input, social bots, and personal assistants were excluded.
- Screening started with about one thousand papers, reduced to 464, then 104, and finally 56 studies after title, abstract, and full-text review; the dataset of included and excluded studies is available in Chaves and Gerosa (2019).
- Analysis used a qualitative coding process inspired by Grounded Theory: one researcher selected relevant statements and labeled them as characteristics, a second researcher reviewed the set, and both discussed merging, renaming, or removing characteristics; quotes were then labeled as benefits, challenges, or strategies.
Limitations
- The paper states it focused on disembodied, text-based chatbots, excluding embodied and speech-based conversational agents, which may underrepresent domains such as Ambient Intelligence and Software Engineering.
- The paper states the definition of chatbot is not consolidated, so some studies with relevant social aspects may not have been found despite using several synonyms and Google Scholar.
- The paper states the conceptual model was derived through qualitative coding and relies on researchers’ subjective assessment, mitigated by in-person consensus discussions; it also notes that most surveyed results are exploratory and that strategies for moral agency and thoroughness were not identified.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
0 of 425 cited sources checked · 0 supported · 0 flagged
- Findingown data§ 2. Overview of the surveyed literature
Among studies that adopted real chatbots, 18 studies analyze logs of conversations or users' perceptions of third-party chatbots such as Cleverbot, Talkbot, and Woebot.
“among them, 18 studies analyze logs of conversations or users' perceptions of third-party chatbots such as Cleverbot (e.g., Corti and Gillespie (2016)), Talkbot (e.g., Brahnam and De Angeli (2012)), and Woebot K. K. Fitzpatrick et al. (2017).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Corti and Gillespie (2016)
Not checked in the free run.
- cites Brahnam and De Angeli (2012)
Not checked in the free run.
- cites K. K. Fitzpatrick et al. (2017)
Not checked in the free run.
- Findingown data§ 1. Introduction
From an analysis of 56 scientific studies, the survey derives a conceptual model of social characteristics.
“From our analysis of 56 scientific studies, we derive a conceptual model of social characteristics, aiming to help researchers and designers identify the subset of characteristics that are relevant to their context and how adopting-or neglecting-a particular characteristic may influence the way humans perceive the chatbots.”
Quote in the paperSubstantial claim- Rests on an assumption: A lack of studies brings together the social characteristics that influence the way users perceive and behave toward chatbots.
- Findingown data§ 2. Overview of the surveyed literature
Most papers (59%) focus on task-oriented chatbots.
“Most papers (59%) focus on task-oriented chatbots.”
Quote in the paperNot a substantial claim - Findingown data§ 3.1.1. Proactivity
The survey found 18 papers that report either chatbots with proactive behavior or implications of manifesting a proactive behavior.
“In this survey, we found 18 papers that report either chatbots with proactive behavior or implications of manifesting a proactive behavior.”
Quote in the paperNot a substantial claim - Findingown data§ 3.1.1. Proactivity
Proactivity was mostly investigated in open domain and education chatbots (four studies each).
“Proactivity was mostly investigated in open domain and education chatbots (four studies each).”
Quote in the paperNot a substantial claim
- Findingnone given§ 3.1. Conversational Intelligence
Most of the studies rely on data that comes from the log of the conversations, interviews, and questionnaires.
“Most of the studies rely on data that comes from the log of the conversations, interviews, and questionnaires.”
Quote in the paperNot a substantial claim - Findingnone given§ 3.1.1. Proactivity
Proactivity was also observed in eight other task-oriented domains, including task management and information searches.
“Proactivity was also observed in eight other task-oriented domains, including task management and information searches as can be observed in the supplementary materials.”
Quote in the paperNot a substantial claim - Findingnone given§ 3.1.1. Proactivity
Research in open domain chatbots has reported most of the social characteristics, except for Communicability.
“Research in open domain chatbots has reported most of the social characteristics, except for Communicability .”
Quote in the paperNot a substantial claim - Findingown data§ 3.1.1. Proactivity
Proactivity (also addressed as 'intervention mode') was explicitly addressed in seven studies.
“Proactivity (also addressed as ' intervention mode ') was explicitly addressed in seven studies (Avula et al., 2018; Chaves & Gerosa, 2018; Dyke et al., 2013; Hayashi, 2015; V. Q. Liao et al., 2016; Schuetzler et al., 2018; Tegos et al., 2016).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Avula et al., 2018
Not checked in the free run.
- cites Chaves & Gerosa, 2018
Not checked in the free run.
- cites Dyke et al., 2013
Not checked in the free run.
- Findingown data§ 2. Overview of the surveyed literature
The conceptual model of chatbots' social characteristics groups eleven characteristics into three main categories, depending on whether the social characteristic relates to the chatbot's conversational behavior, social protocols, or virtual representation.
“Eleven characteristics found in the literature were grouped into three main categories, depending on whether the social characteristic relates to the chatbot's conversational behavior, social protocols, or virtual representation.”
Quote in the paperSubstantial claim - Findingown data§ 3.2. Social Intelligence
We found more studies where the focus of the investigation relates to a specific social characteristic, particularly moral agency and emotional intelligence, when compared to the conversational intelligence category.
“we found more studies where the focus of the investigation relates to a specific social characteristic, particularly moral agency and emotional intelligence , when compared to the conversational intelligence category”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.1. Damage control
Damage control was also identified in other six domains, such as task management and financial services.
“Damage control was also identified in other six domains (see the supplementary materials), such as task management and financial services.”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.1. Damage control
In this survey, we found 12 studies that discuss damage control as a relevant characteristic for chatbots.
“In this survey, we found 12 studies that discuss damage control as a relevant characteristic for chatbots”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.1. Damage control
Two of the 12 studies focus on conflict situations, such as testing and flaming.
“two of which focus on conflict situations, such as testing and flaming (Silvervarg & J¨ onsson, 2013; Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
- cites Wallis & Norling, 2005
Not checked in the free run.
- Findingcitation§ 3.2.1. Damage control
In the remaining studies, needs for damage control emerged from the analysis of conversational logs and users' feedback.
“In the remaining studies (Curry & Rieser, 2018; De Angeli, Johnson, & Coventry, 2001; Duijst, 2017; Gnewuch et al., 2017; Jain, Kumar, et al., 2018; Jenkins et al., 2007; Lasek & Jessa, 2013; Q. V. Liao et al., 2018; M¨ aurer & Weihe, 2015; Toxtli et al., 2018), needs for damage control emerged from the analysis of conversational logs and users' feedback.”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.2. Thoroughness
Three of the 13 papers investigate how patterns of language influence users' perceptions and behavior toward the chatbots.
“three of which investigate how patterns of language influence users' perceptions and behavior toward the chatbots (Duijst, 2017; Hill et al., 2015; Mairesse & Walker, 2009)”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Hill et al., 2015
Not checked in the free run.
- cites Mairesse & Walker, 2009
Not checked in the free run.
- Findingown data§ 3.2.2. Thoroughness
We found 13 papers that report the importance of thoroughness in chatbot design.
“We found 13 papers that report the importance of thoroughness in chatbot design”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.3. Manners
The survey did not find studies focusing on personal conversation strategies such as addressing users by name.
“In addition, the literature points to needs for personal conversations (e.g., addressing the users by name), but we did not find studies that focus on this type of strategy.”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.3. Manners
There is a lack of studies on the rationality around the strategies with politeness models used in human-human social interactions.
“but there is a lack of studies on the rationality around the strategies with politeness models used in human-human social interactions (Wallis & Norling, 2005).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
- Findingown data§ 3.2.4. Moral agency
Moral agency was observed in only two domains of studies: open domain (four studies) and race-talk (two studies).
“Moral agency was observed in only two domains of studies: open domain (four studies) and race-talk (two studies), which shows that this characteristic is primarily relevant when the conversational topic may raise moral concerns, which ultimately requires ethical behavior from the conversational partners.”
Quote in the paperSubstantial claim - Findingreasoning§ 3.2.3. Manners
Manners are under-investigated in the chatbot literature.
“Although the literature emphasizes that manners are important to approximate chatbot interactions to human conversational protocols, this social characteristic is under-investigated in the literature.”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.2. Thoroughness
Thoroughness is mainly reported for open domain (five studies) and customer service chatbots (two studies), where the interactions are expected to be natural and credible to succeed.
“Thoroughness is mainly reported for open domain (five studies) and customer service chatbots (two studies), where the interactions are expected to be natural and credible to succeed (Gnewuch et al., 2017; Morrissey & Kirakowski, 2013).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
- Findingcitation§ 3.2.4. Moral agency
In four studies, authors investigated chatbots' ability to handle conversations where persistence of gender and racial stereotypes may occur.
“In four studies, the authors investigated the ability of chatbots to handle conversations where the persistence of gender (Brahnam & De Angeli, 2012; De Angeli & Brahnam, 2006) and racial stereotypes (Marino, 2014; Schlesinger et al., 2018) may occur.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Brahnam & De Angeli, 2012
Not checked in the free run.
- cites De Angeli & Brahnam, 2006
Not checked in the free run.
- cites Marino, 2014
Not checked in the free run.
- Findingown data§ 3.2.4. Moral agency
The survey found six papers that address moral agency.
“We found six papers that address moral agency .”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.2. Thoroughness
Log of conversations revealed issues regarding thoroughness in two studies.
“Log of conversations revealed issues regarding thoroughness in two studies (Coniam, 2008; Jenkins et al., 2007).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Coniam, 2008
Not checked in the free run.
- cites Jenkins et al., 2007
Not checked in the free run.
- Findingown data§ 3.2.2. Thoroughness
Thoroughness was also reported in another six domains of studies, such as financial services and education.
“Thoroughness was also reported in another six domains of studies, such as financial services and education (see the supplementary materials).”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.2. Thoroughness
In the remaining papers, thoroughness emerged from interviews and users' subjective feedback.
“In the remaining papers, thoroughness emerged from interviews and users' subjective feedback (Chaves & Gerosa, 2018; Kirakowski et al., 2009; Morrissey & Kirakowski, 2013; Tallyn et al., 2018; Thies et al., 2017; Zamora, 2017).”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.5. Emotional Intelligence
Emotional intelligence is mainly investigated in domains where topics may involve disclosure of feelings and expressions of empathy and understanding are appropriate.
“Emotional intelligence is mainly investigated in domains where topics may involve the disclosure of feelings (e.g., in open domain interactions (Shum et al., 2018)) and expressions of empathy and understanding are appropriate (Dohsaka et al., 2014; K. K. Fitzpatrick et al., 2017) (e.g., health care, gaming, education).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Shum et al., 2018
Not checked in the free run.
- cites Dohsaka et al., 2014
Not checked in the free run.
- cites K. K. Fitzpatrick et al., 2017
Not checked in the free run.
- Findingown data§ 3.2.4. Moral agency
The survey did not find strategies to address moral agency issues.
“Despite the relevance of moral agency to the development of socially intelligent chatbots, we did not find strategies to address the issues.”
Quote in the paperSubstantial claim - Findingown data§ 3.2.5. Emotional Intelligence
Most studies on emotional intelligence focused on understanding the effects of chatbots' empathy and emotional self-disclosure.
“Unlikely the previously discussed categories, most studies on emotional intelligence focused on understanding the effects of chatbots' empathy and emotional self-disclosure (Ayedoun et al., 2017; Dohsaka et al., 2014; K. K. Fitzpatrick et al., 2017; Ho et al., 2018; Kumar et al., 2010; S. Lee & Choi, 2017; Miner et al., 2016; Morris, 2002; Portela & Granell-Canut, 2017; Shum et al., 2018; Wallis &”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.5. Emotional Intelligence
Affective utterances toward the user are a common strategy to demonstrate emotional intelligence.
“affective utterances toward the user are a common strategy to demonstrate emotional intelligence .”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.5. Emotional Intelligence
The survey identified 14 studies that report emotional intelligence.
“We identified 14 studies that report emotional intelligence .”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.6. Personalization
Three studies pose personalization as a research goal.
“Three studies pose personalization as a research goal (Duijst, 2017; V. Q. Liao et al., 2016; Shum et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites V. Q. Liao et al., 2016
Not checked in the free run.
- cites Shum et al., 2018
Not checked in the free run.
- Findingown data§ 3.2.6. Personalization
In most studies, personalization was observed in exploratory findings.
“In most of the studies, though, personalization was observed in exploratory findings.”
Quote in the paperNot a substantial claim - Findingcitation§ actions:
The main challenge regarding personalization is privacy.
“According to the surveyed literature, the main challenge regarding personalization is [C1] privacy .”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.6. Personalization
The survey found 11 studies that report personalization.
“We found 11 studies that report personalization .”
Quote in the paperNot a substantial claim - Findingown data§ 3.2.6. Personalization
Personalization was investigated in seven different domains, including open domain and task management (two studies each).
“Personalization was investigated in seven different domains, including open domain and task management (two studies each).”
Quote in the paperNot a substantial claim - Findingcitation§ 3.2.6. Personalization
In two studies, needs for personalization emerged from conversational logs.
“In two studies (Lasek & Jessa, 2013; Toxtli et al., 2018), needs for personalization emerged from the conversational logs.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
- cites Toxtli et al., 2018
Not checked in the free run.
- Findingcitation§ 3.2.6. Personalization
In six studies, personalization emerged from analysis of interviews and participants' self-reported feedback.
“In six studies, personalization emerged from the analysis of interviews and participants' self-reported feedback (Duijvelshoff, 2017; Jenkins et al., 2007; Neururer et al., 2018; Portela & Granell-Canut, 2017; Tallyn et al., 2018; Thies et al., 2017).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijvelshoff, 2017
Not checked in the free run.
- cites Jenkins et al., 2007
Not checked in the free run.
- cites Neururer et al., 2018
Not checked in the free run.
- Findingcitation§ actions:
Both benefits and strategies identified in the literature are in line with types of personalization proposed by Fan and Poole (2006).
“Both the benefits and strategies identified in the literature are in line with the types of personalization proposed by Fan and Poole (2006).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Fan and Poole (2006)
Not checked in the free run.
- Findingcitation§ 3.3.1. Identity
In three studies, qualitative analysis of conversational logs revealed that participants put effort into understanding aspects of chatbots' identity.
“In three studies (Neururer et al., 2018; Silvervarg & J¨ onsson, 2013; Thies et al., 2017; Toxtli et al., 2018), qualitative analysis of conversational logs revealed that participants put effort into understanding aspects of the chatbots' identity .”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Neururer et al., 2018
Not checked in the free run.
- cites Silvervarg & J¨ onsson, 2013
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- Findingown data§ 3.3.1. Identity
Identity concerns were primarily investigated for open domain and customer service chatbots (four studies each).
“Identity concerns were primarily investigated for open domain and customer service chatbots (four studies each).”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. The importance of conversational context
We found conscientiousness, damage control, thoroughness, manners, emotional intelligence, and identity in studies for both education and customer services domains.
“We found conscientiousness, damage control, thoroughness, manners, emotional intelligence, and identity in studies for both domains.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. The importance of conversational context
The only characteristic that was not investigated in an open domain was communicability.
“The only characteristic that was not investigated in an open domain was communicability.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. The importance of conversational context
Moral agency is the only characteristic that does not show up across several domains.
“Moral agency is the only characteristic that does not show up across several domains.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. The importance of conversational context
Education and customer services literature report the greatest number of characteristics.
“Education and customer services literature report the greatest number of characteristics, but this result might be influenced by the maturity of the research in chatbots for these domains.”
Quote in the paperNot a substantial claim - Findingown data§ 4.2. The importance of conversational context
Almost all social characteristics (10 out of 11) were found in studies related to conversations not restricted to a specific domain (open domain).
“As Table 2 depicts 2 , almost all social characteristics (10 out of 11) were found in studies related to conversations not restricted to a specific domain (open domain):”
Quote in the paperSubstantial claim - Findingnone given§ 4.2. The importance of conversational context
Education and customer services are the task-oriented domains most reported in the literature.
“As we pointed out in Section 2, education and customer services are the task-oriented domains most reported in the literature.”
Quote in the paperNot a substantial claim - Findingnone given§ 7. Conclusion
We could not identify strategies to manifest moral agency and thoroughness.
“In this sense, we highlight that we could not identify strategies to manifest moral agency and thoroughness, although strategies for several other characteristics are also under-investigated.”
Quote in the paperSubstantial claim - Premisecitation§ 1. Introduction
Chatbots still fail to meet users' expectations.
“However, chatbots still fail to meet users' expectations (Brandtzaeg & Følstad, 2018; Jain, Kumar, Kota, & Patel, 2018; Luger & Sellen, 2016; Zamora, 2017).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Brandtzaeg & Følstad, 2018
Not checked in the free run.
- cites Jain, Kumar, Kota, & Patel, 2018
Not checked in the free run.
- cites Luger & Sellen, 2016
Not checked in the free run.
- Premisecitation§ 1. Introduction
When chatbots do not meet these expectations, the user may experience frustration and dissatisfaction.
“When chatbots do not meet these expectations, the user may experience frustration and dissatisfaction (Luger & Sellen, 2016; Zamora, 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Luger & Sellen, 2016
Not checked in the free run.
- cites Zamora, 2017
Not checked in the free run.
- Premisecitation§ 1. Introduction
The literature has consistently suggested that chatbots' interactional goals should also include social capabilities.
“the literature has consistently suggested that chatbots' interactional goals should also include social capabilities (Jain, Kumar, et al., 2018; Q. V. Liao et al., 2018).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Q. V. Liao et al., 2018
Not checked in the free run.
- Premisecitation§ 1. Introduction
People prefer agents who demonstrate a positive attitude and mood.
“and demonstrate a positive attitude and mood (Thies, Menon, Magapu, Subramony, & O'neill, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies, Menon, Magapu, Subramony, & O'neill, 2017
Not checked in the free run.
- Premisecitation§ 1. Introduction
People prefer agents who self-disclose and show reciprocity when recommending.
“self-disclose and show reciprocity when recommending (S. Lee & Choi, 2017);”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites S. Lee & Choi, 2017
Not checked in the free run.
- Premisecitation§ 1. Introduction
According to the Media Equation theory, people naturally respond to social situations when interacting with computers.
“According to the Media Equation theory (Reeves & Nass, 1996), people naturally respond to social situations when interacting with computers (Fogg, 2003; Nass, Steuer, & Tauber, 1994).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Reeves & Nass, 1996
Not checked in the free run.
- cites Fogg, 2003
Not checked in the free run.
- cites Nass, Steuer, & Tauber, 1994
Not checked in the free run.
- Premisecitation§ 1. Introduction
People prefer agents who conform to gender stereotypes associated with tasks.
“Studies on chatbots have shown that people prefer agents who: conform to gender stereotypes associated with tasks (Forlizzi, Zimmerman, Mancuso, & Kwak, 2007);”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Forlizzi, Zimmerman, Mancuso, & Kwak, 2007
Not checked in the free run.
- Study design and conductown data§ ABSTRACT
The survey analyzed 56 papers from various domains.
“We analyzed 56 papers from various domains to understand how social characteristics can benefit human-chatbot interactions and identify the challenges and strategies to designing them.”
Quote in the paperSubstantial claim - Study design and conductreasoning§ 2. Overview of the surveyed literature
The conceptual model was derived using a qualitative coding process inspired by methods such as Grounded Theory (open coding stage).
“Noticeably, the characteristics and categories are seldom explicitly highlighted to in the literature, so the conceptual model was derived using a qualitative coding process inspired by methods such as Grounded Theory (Auerbach & Silverstein, 2003) (open coding stage).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Auerbach & Silverstein, 2003
Not checked in the free run.
- Rests on an assumption: The characteristics and categories are seldom explicitly highlighted in the literature.
- Premisecitation§ 3.1.1. Proactivity
In particular domains, proactivity helps chatbots to either guide users or establish and monitor users' goals.
“in particular domains, proactivity helps chatbots to either guide users or establish and monitor users' goals.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites K. K. Fitzpatrick et al., 2017
Not checked in the free run.
- cites M¨ aurer & Weihe, 2015
Not checked in the free run.
- cites Tallyn et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Proactivity is employed to naturally recover from a failure.
“in Portela and Granell-Canut (2017) and Silvervarg and J¨ onsson (2013), proactivity is employed to naturally recover from a failure.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Portela & Granell-Canut, 2017
Not checked in the free run.
- cites Silvervarg & J¨ onsson, 2013
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
In task-oriented interactions, proactivity can improve the conversation's productivity.
“in task-oriented interactions, such as searching or shopping, proactivity can improve the conversation's productivity (Jain, Kumar, et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Educational chatbots rely on proactivity to prompt students to think, share, and collaborate.
“Educational chatbots rely on proactivity to prompt students to think, share, and collaborate (e.g., Dyke et al. (2013)).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dyke et al. (2013)
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
In open domain chatbots, proactivity helps improve engagement by introducing new topics to keep the conversation alive.
“In open domain chatbots, proactivity helps improve engagement by introducing new topics to keep the conversation alive (Shum et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Proactivity in chatbots adds value to interactions.
“literature reveals that proactivity in chatbots adds value to interactions (Avula et al., 2018; Morrissey & Kirakowski, 2013; Thies et al., 2017).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Avula et al., 2018
Not checked in the free run.
- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
The complexity of the task compromised the experience and satisfaction in using the chatbot.
“where the complexity of the task compromised the experience and satisfaction in using the chatbot.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Dyke et al., 2013
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
Conscientiousness influences chatbots' perceived humanness and social presence.
“Schuetzler et al. (2018) showed that conscientiousness also influences chatbots' perceived humanness and social presence.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Schuetzler et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
In a work-related group chat, privacy concerns were observed regarding the chatbot 'reading' the employees' conversations to proactively act.
“in a work-related, group chat, Duijvelshoff (2017) observed privacy concerns regarding the chatbot 'reading' the employees' conversations to proactively act.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijvelshoff, 2017
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Leveraging the conversational context is the most frequent strategy to provide proactivity.
“Leveraging the conversational context is the most frequent strategy (Avula et al., 2018; Chaves & Gerosa, 2018; Duijvelshoff, 2017; Shum et al., 2018; Thies et al., 2017)”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Avula et al., 2018
Not checked in the free run.
- cites Chaves & Gerosa, 2018
Not checked in the free run.
- cites Duijvelshoff, 2017
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
Communication strategies, combined with affective backchannel, are effective in motivating students to communicate and maintain the task flow.
“Statistical results show that the communication strategies, combined with affective backchannel (which is detailed in Section 3.2.5), are effective in motivating students to communicate and maintain the task flow.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ayedoun et al., 2017
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Proactivity can be annoying when the chatbot conveys the impression of trying to control the user.
“proactivity can be annoying when the chatbot conveys the impression of trying to control the user.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Tallyn et al., 2018
Not checked in the free run.
- cites Toxtli et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
When a chatbot does not interpret the meaning and intent of users' utterances, the best-selected response may still sound irrelevant to the conversation.
“as the chatbot does not interpret the meaning and the intent of users' utterances, the best-selected response may still sound irrelevant to the conversation (Coniam, 2008; Duijst, 2017; Dyke et al., 2013).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Coniam, 2008
Not checked in the free run.
- cites Duijst, 2017
Not checked in the free run.
- cites Dyke et al., 2013
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Proactive messages relate to contextual information provided in the conversation to increase the usefulness of interventions.
“in which proactive messages relate to contextual information provided in the conversation to increase the usefulness of interventions (Avula et al., 2018; Duijvelshoff, 2017; Shum et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Avula et al., 2018
Not checked in the free run.
- cites Duijvelshoff, 2017
Not checked in the free run.
- cites Shum et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.1. Proactivity
Untimely and irrelevant proactive messages may compromise the success of the interaction.
“untimely and irrelevant proactive messages may compromise the success of the interaction.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Portela & Granell-Canut, 2017
Not checked in the free run.
- cites V. Q. Liao et al., 2016
Not checked in the free run.
- cites Chaves & Gerosa, 2018
Not checked in the free run.
- Premisecitation§ 3.1.3. Communicability
Ability-check questions can be considered signals of users struggling with functional affordances.
“quantitative results evidenced that ability-check questions can be considered signals of users struggling with functional affordances.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.3. Communicability
Communicability strategies are effective at providing clues about the chatbot's features and ideas about what to do and how.
“A semiotic inspection of news-related chatbots (Val´ erio et al., 2017) evidenced that communicability strategies are effective at providing clues about the chatbot's features and ideas about what to do and how.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
User-interface resources-such as quick replies, cards, and carousels-are used to structure the conversation and reduce issues regarding understanding.
“user-interface resources-such as quick replies, cards, and carousels-are used to structure the conversation and reduce issues regarding understanding (Duijst, 2017; Jain, Kumar, et al., 2018; Tallyn et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Tallyn et al., 2018
Not checked in the free run.
- Premisecitation§ 3.1.2. Conscientiousness
A chatbot for shopping that shows a context window on the side of the conversation outperformed a default chatbot (without the context window) for mental demand and effort constructs.
“A survey showed that the chatbot outperformed a default chatbot (without the context window) for mental demand and effort constructs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kota, et al., 2018
Not checked in the free run.
- Interpretationreasoning§ 3.1.2. Conscientiousness
The more conscientiousness a chatbot manifests, the more it can be perceived as attentive, organized, and efficient.
“the more conscientiousness a chatbot manifests, the more it can be perceived as attentive, organized, and efficient.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.1.3. Communicability
The lack of communicability may lead users to give up on using the chatbot when they cannot understand the available functionalities and how to use them.
“The lack of communicability may lead users to give up on using the chatbot when they cannot understand the available functionalities and how to use them (Val´ erio et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
- Interpretationreasoning§ 3.1.3. Communicability
Communicability helps users gain a sense of which type of messages or functionalities a chatbot can handle.
“Therefore, communicability helps users gain a sense of which type of messages or functionalities a chatbot can handle.”
Quote in the paperSubstantial claim - Premisenone given§ 3.1.2. Conscientiousness
Failing to demonstrate understanding about the users' individual utterances, the conversational context, and the interactional goals results in frustration and loss of credibility.
“The surveyed literature supports that failing to demonstrate understanding about the users' individual utterances, the conversational context, and the interactional goals results in frustration and loss of credibility.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.1.3. Communicability
Some chatbots responded differently depending on whether the user accesses a visual element in the user-interface or types the desired functionality in the text-input box, even if both input modes result in the same utterance.
“in the semiotic engineering evaluation, Val´ erio et al. (2017) observed that some chatbots responded differently depending on whether the user accesses a visual element in the user-interface or types the desired functionality in the text-input box, even if both input modes result in the same utterance.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
- Interpretationreasoning§ 3.1.2. Conscientiousness
The maxims of relation and manner can contribute to the design of conscientious chatbots.
“Particularly, the maxims of relation (the ability to be relevant) and manner (the ability to be clear and orderly) can contribute to the design of conscientious chatbots.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.1. Damage control
When talking to a chatbot, humans are more likely to harass.
“When talking to a chatbot, humans are more likely to harass (Hill et al., 2015)”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Hill et al., 2015
Not checked in the free run.
- Interpretationcitation§ 3.2.1. Damage control
Satisfaction is influenced by the ability to provide a clever response when the user tests the chatbot.
“which shows that satisfaction is influenced by the ability to provide a clever response when the user tests the chatbot”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.1. Damage control
Abusive behavior is often used to test chatbots' social reactions.
“abusive behavior is often used to test chatbots' social reactions (Lasek & Jessa, 2013; Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
- cites Wallis & Norling, 2005
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Providing damage control in chatbots has the benefit of appropriately responding to harassment.
“[B1] to appropriately respond to harassment”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.1. Damage control
When a chatbot does not respond appropriately, it ultimately leads the conversation to fail.
“which ultimately leads the conversation to fail (Jain, Kumar, et al., 2018)”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
When a chatbot does not respond appropriately, it may disappoint the user.
“or disappoint the user (Jain, Kumar, et al., 2018; M¨ aurer & Weihe, 2015)”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Mäurer & Weihe, 2015
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Chatbots are more likely to be targets of profanity than humans would.
“chatbots are more likely to targets of profanity than humans would (Hill et al., 2015)”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Hill et al., 2015
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Chatbots respond to harassment in a variety of ways, including nonsensical, negative, and positive responses.
“The results show that chatbots respond to harassment in a variety of ways, including nonsensical, negative, and positive responses.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
When a chatbot does not respond appropriately, it may encourage abusive behavior.
“When a chatbot does not respond appropriately, it may encourage the abusive behavior (Curry & Rieser, 2018)”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
- Interpretationcitation§ 3.2.1. Damage control
There is a limit to which damage control strategies will be effective to avoid testing and abuse.
“Thus, there is a limit to which damage control strategies will be effective to avoid testing and abuse.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.1. Damage control
When talking to a chatbot, humans are more likely to test the agent's capabilities and knowledge.
“test the agent's capabilities and knowledge (Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
First-time users appreciated when the chatbot successfully performed tasks when the user expected the chatbot to fail.
“first-time users appreciated when the chatbot successfully performed tasks when the user expected the chatbot to fail”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
When talking to a chatbot, humans are more likely to feel disappointed with mistakes.
“feel disappointed with mistakes (Jain, Kumar, et al., 2018; M¨ aurer & Weihe, 2015)”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Mäurer & Weihe, 2015
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
In task-oriented scenarios, the lack of linguistic knowledge may lead the chatbots to get lost in the conversational workflow, compromising the success of the interaction.
“In task-oriented scenarios, the lack of linguistic knowledge may lead the chatbots to get lost in the conversational workflow (Gnewuch et al., 2017), compromising the success of the interaction.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
The literature has shown that interactions with conversational agents are not quite equal to human-human interactions.
“the literature has shown that interactions with conversational agents are not quite equal to humanhuman interactions (Luger & Sellen, 2016; Mou & Xu, 2017; Shechtman & Horowitz, 2003)”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Luger & Sellen, 2016
Not checked in the free run.
- cites Mou & Xu, 2017
Not checked in the free run.
- cites Shechtman & Horowitz, 2003
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Providing damage control in chatbots has the benefit of dealing with lack of knowledge.
“[B3] to deal with lack of knowledge”
Quote in the paperNot a substantial claim - Interpretationcitation§ 3.2.1. Damage control
It is unlikely that chatbots interactions will evolve to be conflict-free.
“Hence, it is unlikely that chatbots interactions will evolve to be conflict-free.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.1. Damage control
Describing chatbot's capabilities after failures in the dialogue was appreciated by first-time users.
“Jain, Kumar, et al. (2018) showed that describing chatbot's capabilities after failures in the dialogue was appreciated by first-time users.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Data-driven chatbots often provide non-coherent responses to harassment.
“Curry and Rieser (2018) shows that data-driven chatbots often provide non-coherent responses to harassment.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Regarding interpersonal conflicts, the strategies are in line with the theory on human-human communication, which includes non-negotiation, emotional appeal, personal rejection, and emphatic understanding.
“Regarding interpersonal conflicts, the strategies are in line with the theory on human-human communication, which includes non-negotiation, emotional appeal, personal rejection, and emphatic understanding (M. A. Fitzpatrick & Winke, 1979).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites M. A. Fitzpatrick & Winke, 1979
Not checked in the free run.
- Premisecitation§ 3.2.1. Damage control
Sometimes, these responses conveyed the impression of flirtatious or counter-aggression.
“Sometimes, these responses conveyed the impression of flirtatious or counter-aggression.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
- Interpretationreasoning§ 3.2.1. Damage control
Politeness can be used as a strategy to minimize the effect of lack of knowledge, managing the conversation despite the possible mistakes.
“In this sense, politeness can be used as a strategy to minimize the effect of lack of knowledge (see Section 3.2.3), managing the conversation despite the possible mistakes.”
Quote in the paperNot a substantial claim - Interpretationcitation§ 3.2.1. Damage control
Damage control strategies have different levels of severity.
“Damage control strategies have different levels of severity.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.2. Thoroughness
Human interlocutors were actually matching the patterns of language use with the chatbot, who sent fewer words per message.
“the human interlocutors were actually matching the patterns of language use with the chatbot, who sent fewer words per message”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Hill et al., 2015
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
Most chatbots are built over 'clean' data, where specific words are removed from their dictionary, to prevent reproducing hate speech or abusive talk.
“in order to prevent a chatbot from reproducing hate speech or abusive talk, most chatbots are built over 'clean' data, where specific words are removed from their dictionary (De Angeli & Brahnam, 2006; Schlesinger et al., 2018).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites De Angeli & Brahnam, 2006
Not checked in the free run.
- cites Schlesinger et al., 2018
Not checked in the free run.
- Interpretationreasoning§ 3.2.4. Moral agency
Manifesting moral agency may prevent obnoxious user interactions.
“Manifesting moral agency may, thus, prevent obnoxious user interactions.”
Quote in the paperNot a substantial claim - Interpretationcitation§ 3.2.4. Moral agency
Moral agency may prevent the chatbot itself from being biased or disrespectful to humans.
“In addition, moral agency may prevent the chatbot itself from being biased or disrespectful to humans.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.2. Thoroughness
Participants reported a draining experience when interacting with a chatbot that uses many emojis and letter reduplication, since the chatbot's energy was too high to match.
“participants reported a draining experience, since the chatbot's energy was too high to match”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 3.2.2. Thoroughness
Chatbot utterances are often pre-recorded by the chatbot designer.
“chatbot utterances are often pre-recorded by the chatbot designer (Mairesse & Walker, 2009)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mairesse & Walker, 2009
Not checked in the free run.
- Interpretationreasoning§ 3.2.4. Moral agency
Manifesting moral agency requires a broader understanding of the world, rather than alienation.
“As a consequence, manifesting moral agency requires a broader understanding of the world, rather than alienation, which is an open challenge.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.4. Moral agency
The female character received violent sexual statements and was threatened with rape five times in the analyzed corpora.
“In contrast, the female character received violent sexual statements, and was threatened with rape five times in the analyzed corpora.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli and Brahnam (2006)
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
Absence of racist specific words did not prevent the chatbot Zo from uttering discriminatory exchanges.
“From (Schlesinger et al., 2018), one can notice that the absence of racist specific words did not prevent the chatbot Zo from uttering discriminatory exchanges.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Schlesinger et al., 2018
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
A static image or avatar representing the agent may convey social grouping.
“In addition, a static image (or avatar) representing the agent may convey social grouping (Nowak & Rauh, 2005).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Nowak & Rauh, 2005
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
The lack of moral agency may lead to cases such as Tay, Microsoft's Twitter chatbot, becoming racist, sexist, and harassing in a few hours.
“The lack of this ability may lead to cases such as Tay, Microsoft's Twitter chatbot that became racist, sexist, and harassing in a few hours (Neff & Nagy, 2016).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Neff & Nagy, 2016
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
When avatars were presented as black adults, references to race often deteriorated into racist attacks.
“In Brahnam and De Angeli (2012), when the avatars were presented as black adults, references to race often deteriorated into racist attacks.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Brahnam and De Angeli (2012)
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
Chatbots are often developed using language registers and cultural references of the dominant culture.
“Marino (2014) and Schlesinger et al. (2018) argue that chatbots are often developed using language registers (Marino, 2014) and cultural references (Schlesinger et al., 2018) of the dominant culture.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Marino, 2014
Not checked in the free run.
- cites Schlesinger et al., 2018
Not checked in the free run.
- Interpretationcitation§ 3.2.4. Moral agency
Manifesting moral agency can enrich interpersonal relationships with chatbots.
“Statistical results showed that all the constructs correlate with morality, which suggests that manifesting moral agency can enrich interpersonal relationships with chatbots.”
Quote in the paperSubstantial claim - Interpretationreasoning§ 3.2.4. Moral agency
These chatbots have no knowledge of those words and their meaning.
“These chatbots have no knowledge of those words and their meaning.”
Quote in the paperSubstantial claim - Premisecitation§ 3.2.4. Moral agency
Banks (2018) developed and validated a metric for perceived moral agency in conversational interfaces, including chatbots.
“Banks (2018) developed and validated a metric for perceived moral agency in conversational interfaces, including chatbots.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Banks (2018)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Humans are twice as likely to mirror negative sentiment from a chatbot than from a human.
“In another mental health care study, Miner et al. (2016) found that humans are twice as likely to mirror negative sentiment from a chatbot than from a human, which is a relevant implication for therapeutic interactions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Miner et al. (2016)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Dohsaka et al. (2014) did not find effect of chatbot's self-disclosure on emotional connection.
“Although Dohsaka et al. (2014) did not find effect of chatbot's self-disclosure on emotional connection, S. Lee and Choi (2017) found that self-disclosure and reciprocity significantly improved trust and interactional enjoyment.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
In K. K. Fitzpatrick et al. (2017), seven participants reported that the best thing about their experience with the therapist chatbot was perceived empathy.
“In K. K. Fitzpatrick et al. (2017), seven participants reported that the best thing about their experience with the therapist chatbot was perceived empathy.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites K. K. Fitzpatrick et al. (2017)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Participants in the chatbots condition experienced as many emotional, relational, and psychological benefits as participants who disclosed to a human partner.
“Participants in the chatbots condition experienced as many emotional, relational, and psychological benefits as participants who disclosed to a human partner.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ho et al. (2018)
Not checked in the free run.
- Premisecitation§ 3.2.4. Moral agency
Machine learning algorithms and corpus-based language generation are biased toward the available training datasets.
“as extensively discussed in Schlesinger et al. (2018), machine learning algorithms and corpus-based language generation are biased toward the available training datasets.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Schlesinger et al. (2018)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Participants reported rise of affection when the chatbot remembered something they had said before, even if just the user's name.
“In Portela and GranellCanut (2017), participants reported the rise of affection when the chatbot remembered something they had said before, even if it was just the user's name.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Portela and GranellCanut (2017)
Not checked in the free run.
- Interpretationcitation§ 3.2.5. Emotional Intelligence
Demonstrating conscientiousness may affect the emotional connection between humans and chatbots.
“demonstrating conscientiousness may affect the emotional connection between humans and chatbots.”
Quote in the paperNot a substantial claim - Premisecitation§ 3.2.5. Emotional Intelligence
The perception that the chatbot understands one's feelings may create a sense of belonging and acceptance.
“the perception that the chatbot understands one's feelings may create a sense of belonging and acceptance (Ho et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ho et al., 2018
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Participants negatively rated the degree of emotion in the chatbot's responses in Jenkins et al. (2007).
“The participants negatively rated the degree of emotion in the chatbot's responses.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jenkins et al. (2007)
Not checked in the free run.
- Interpretationcitation§ 3.2.5. Emotional Intelligence
Regulating affective reactions is still a challenge.
“Although emotional intelligence is the goal of several studies, [C1] regulating affective reactions is still a challenge.”
Quote in the paperSubstantial claim - Premisecitation§ 3.2.5. Emotional Intelligence
Self-disclosure and reciprocity significantly improved trust and interactional enjoyment.
“Although Dohsaka et al. (2014) did not find effect of chatbot's self-disclosure on emotional connection, S. Lee and Choi (2017) found that self-disclosure and reciprocity significantly improved trust and interactional enjoyment.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites S. Lee and Choi (2017)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Empathic expressions also improved user ratings of the peer agent regarding intimacy, compassion, amiability, and encouragement.
“In addition, the empathic expressions also improved the user ratings of the peer agent regarding intimacy, compassion, amiability, and encouragement.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
The chatbot in Kumar et al. (2010) has shown only a marginally significant increase in social belonging compared to the same interaction with a human partner.
“Nevertheless, the chatbot has shown an only marginally significant increase in social belonging, when compared to the same interaction with a human partner.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kumar et al. (2010)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Empathic expressions significantly improved user satisfaction.
“The survey results revealed that empathic expressions significantly improved user satisfaction.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Empathic utterances for quiz-style interaction significantly increase the number of users' messages per hint for both answers and non-answer utterances.
“In Dohsaka et al. (2014), empathic utterances for the quiz-style interaction significantly increase the number of users' messages per hint for both answers and non-answer utterances (such as feedback about the success/failure).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
The analysis of conversational logs revealed positive effect of chatbot manifesting social cues and empathic signs as well as touching on personal topics.
“The analysis of the conversational logs revealed the positive effect of the chatbot manifesting social cues and empathic signs as well as touching on personal topics.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Portela and Granell-Canut (2017)
Not checked in the free run.
- Premisecitation§ 3.2.5. Emotional Intelligence
Dohsaka et al. (2014) did not find any effect of self-oriented emotional expressions in users' satisfaction or engagement.
“In contrast, Dohsaka et al. (2014) did not find any effect of self-oriented emotional expressions in the users' satisfaction or engagement.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- Premisecitation§ 3.2.6. Personalization
In open domain interactions, personalization is derived from remembering information from previous interactions, such as personal preferences and users' details.
“In open domain interactions, personalization is derived from remembering information from previous interactions, such as personal preferences and users' details (Thies et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ actions:
Collecting personal data may lead to privacy concerns.
“However, as Duijvelshoff (2017) and Thies et al. (2017) suggest, collecting personal data may lead to privacy concerns.”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Duijvelshoff (2017)
Not checked in the free run.
- cites Thies et al. (2017)
Not checked in the free run.
- Premisecitation§ actions:
Users that start interaction by clicking an option are more likely to continue conversation if the next exchange also has visual elements as optional affordances.
“When evaluating visual elements (such as quick replies) compared to typing the responses, Lasek and Jessa (2013) observed that users that start the interaction by clicking an option are more likely to continue the conversation if the next exchange also has visual elements as optional affordances.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Lasek and Jessa (2013)
Not checked in the free run.
- Premisecitation§ actions:
Providing personalization increases the value of provided information.
“providing personalization increases the value of provided information (Duijst, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst, 2017
Not checked in the free run.
- Premisecitation§ actions:
Interruption is likely associated with users' general aversion to unsolicited messages at work.
“Similarly, qualitative analysis of perceived interruption in a workplace chat (V. Q. Liao et al., 2016) suggests that interruption is likely associated with users' general aversion to unsolicited messages at work.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites V. Q. Liao et al., 2016
Not checked in the free run.
- Premisecitation§ 3.2.6. Personalization
In the chatbot domain, personalization may increase agents' social intelligence, since it allows a chatbot to be aware of situational context and dynamically adapt its features to better suit individual needs.
“In the chatbot domain, personalization may increase the agents' social intelligence, since it allows a chatbot to be aware of situational context and dynamically adapt its features to better suit individual needs (Neururer et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Neururer et al., 2018
Not checked in the free run.
- Premisecitation§ actions:
Participants expressed desire for chatbot to provide different answers to different users.
“In Portela and Granell-Canut (2017), participants expressed the desire for the chatbot to provide different answers to different users.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Portela and Granell-Canut (2017)
Not checked in the free run.
- Premisecitation§ actions:
Users who typed are more likely to abandon conversation when they face options to click.
“In contrast, users who typed are more likely to abandon the conversation when they face options to click.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Lasek and Jessa (2013)
Not checked in the free run.
- Interpretationcitation§ 3.3.1. Identity
Designing and elaborating on a persona is a strategy for attributing identity to chatbots.
“Regarding the strategies, the surveyed literature suggests [S1] to design and elaborate on a persona . Chatbots should have a comprehensive persona and answer agent-oriented conversations with a consistent description of itself (Q. V. Liao et al., 2018; Neururer et al., 2018).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Q. V. Liao et al. (2018)
Not checked in the free run.
- cites Neururer et al. (2018)
Not checked in the free run.
- cites De Angeli (2005)
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
The identity of a partner (even if only perceived) gives rise to new processes, expectations, and effects that influence outcomes of interaction.
“The identity of a partner (even if only perceived) gives rise to new processes, expectations, and effects that influence the outcomes of the interaction (Ho et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ho et al., 2018
Not checked in the free run.
- Interpretationcitation§ 3.3.1. Identity
Attributing identity to a chatbot increases human-likeness.
“[B2] to increase human-likeness: some attributes may convey a perceived human-likeness. Araujo (2018) showed that using human-like language style, name, and greetings resulted in significantly higher scores for naturalness.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Araujo (2018)
Not checked in the free run.
- cites Candello et al. (2017)
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
In open domain interactions, identity is explored as a means of building common ground.
“In open domain interactions, identity is explored as a means of building common ground (De Angeli, Johnson, & Coventry, 2001).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli, Johnson, & Coventry, 2001
Not checked in the free run.
- Interpretationcitation§ 3.3.1. Identity
Attributing identity to a chatbot risks reinforcing negative stereotypes.
“[C1] to avoid negative stereotypes: when engaging in a conversation, interlocutors base their behavior on common ground (joint knowledge, background facts, assumptions, and beliefs that participants have of each other) (see (De Angeli, Johnson, & Coventry, 2001)).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites De Angeli, Johnson, & Coventry (2001)
Not checked in the free run.
- cites De Angeli (2005)
Not checked in the free run.
- cites Brahnam & De Angeli (2012)
Not checked in the free run.
- Premisecitation§ 3.3. Personification
The more human-like a computer representation is, the more social people's responses will be.
“and (ii) the more human-like a computer representation is, the more social people's responses will be (Gong, 2008).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gong, 2008
Not checked in the free run.
- Premisecitation§ 3.3. Personification
Users can be induced to behave as if computers were humans, even when they consciously know better.
“Indeed, the literature shows that (i) users can be induced to behave as if computers were humans, even when they consciously know better (Nass, Steuer, Tauber, & Reeder, 1993);”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Nass, Steuer, Tauber, & Reeder, 1993
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
In customer services, identity helps manifest credibility and trust.
“In the case of customer services, identity helps manifest credibility and trust (Gnewuch et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
- Premisecitation§ actions:
Zamora (2017) found 16 mentions to personalized interactions, where participants demonstrated need for chatbot to be aware of personal quirks and anticipate needs.
“When evaluating the user's experience with a virtual assistant chatbot, Zamora (2017) found 16 mentions to personalized interactions, where participants demonstrated the need for a chatbot to be aware of their personal quirks and anticipate their needs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zamora (2017)
Not checked in the free run.
- Interpretationcitation§ 3.3.2. Personality
Using appropriate language is a strategy for manifesting personality in chatbots.
“[S1] to use appropriate language: Shum et al. (2018) and Morris (2002) suggest that the chatbot language should be consistently influenced by its personality .”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Shum et al. (2018)
Not checked in the free run.
- cites Morris (2002)
Not checked in the free run.
- cites Mairesse and Walker (2009)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
When proactive messages are based on the context, proactivity increases perceived conscientiousness.
“When the proactive messages are based on the context, proactivity increases perceived conscientiousness (P2) (Thies et al., 2017), since the proactive messages may demonstrate attention to the topic.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Q. V. Liao et al. (2018) found that agent-oriented conversations (asking about an agent's traits and status) are consistent with the tendency to anthropomorphize the agent and engage in chit-chat.
“when evaluating signals of playful interactions, Q. V. Liao et al. (2018) found that agent-oriented conversations (asking about an agent's traits and status) are consistent with the tendency to anthropomorphize the agent and engage in chit-chat.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al. (2018)
Not checked in the free run.
- Interpretationcitation§ 3.3.2. Personality
Attributing personality to a chatbot enriches interpersonal relationships.
“[B2] to enrich interpersonal relationships: chatbots personality can make the interaction more enjoyable (Brandtzaeg & Følstad, 2017; Jain, Kumar, et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Brandtzaeg & Følstad (2017)
Not checked in the free run.
- cites Jain, Kumar, et al. (2018)
Not checked in the free run.
- cites Thies et al. (2017)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Some personality traits require personalization to adapt to the interlocutors' culture and interests.
“Some personality traits require personalization (P9) to adapt to the interlocutors' culture and interests (Ptaszynski et al., 2010).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ptaszynski et al., 2010
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Conscientiousness manifests personalization.
“In addition, conscientiousness manifests personalization (P7) (Jain, Kumar, et al., 2018; Thies et al., 2017) because a chatbot can remember individual preferences within and across sessions.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Racist attacks were observed in interactions with black-representing chatbots.
“racist attacks were observed in interactions with black-representing chatbots.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Brahnam and De Angeli (2012)
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Araujo (2018) noticed that using informal language, having a human name, and using greetings associated with human communication resulted in significantly higher scores for adjectives like likeable, friendly, and personal.
“When comparing human-like vs. machine-like language style, greetings, and framing, Araujo (2018) noticed that using informal language, having a human name, and using greetings associated with human communication resulted in significantly higher scores for adjectives like likeable, friendly, and personal.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Araujo (2018)
Not checked in the free run.
- Interpretationcitation§ 3.3.2. Personality
Attributing personality to a chatbot requires balancing personality traits.
“[C2] to balance personality traits: Thies et al. (2017) observed that users prefer a proactive, productive, witty chatbot. Yet, they also would like them to be caring, encouraging, and exciting.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Thies et al. (2017)
Not checked in the free run.
- cites Mairesse and Walker (2009)
Not checked in the free run.
- cites Sjödén et al. (2011)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Emotional intelligence influences perceived personality.
“Emotional intelligence influences perceived personality (P8) , since chatbots' personality traits affect the intensity of emotional reactions (Morris, 2002; Thies et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Morris, 2002
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Personalization benefits identity.
“Besides, personalization benefits identity (P10) , since the users' social-agent orientation may require a chatbot to adapt the level of engagement in small talk and the agent's visual representation (Jenkins et al., 2007; V. Q. Liao et al., 2016).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jenkins et al., 2007
Not checked in the free run.
- cites V. Q. Liao et al., 2016
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Conscientiousness manifests emotional intelligence.
“Conscientiousness manifests emotional intelligence (P6) since retaining information from previous turns and being able to recall them demonstrates empathy (Jain, Kumar, et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Conscientiousness facilitates damage control.
“Conscientiousness facilitates damage control (P13) , since the attention to the workflow and context may increase the ability to recover from a failure without restarting the workflow (Duijst, 2017; Dyke et al., 2013; Gnewuch et al., 2017; Jain, Kota, et al., 2018).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Dyke et al., 2013
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
- Interpretationcitation§ 3.3.2. Personality
Having a sense of humor is a strategy for manifesting personality in chatbots.
“[S2] to have a sense of humor: literature highlights humor as a positive personality trait (Meany & Clark, 2010).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Meany & Clark (2010)
Not checked in the free run.
- cites Jain, Kumar, et al. (2018)
Not checked in the free run.
- cites Ptaszynski et al. (2010)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Personalization manifests thoroughness.
“Personalization manifests thoroughness (P15) (Duijst, 2017; Gnewuch et al., 2017; Hill et al., 2015; Thies et al., 2017), since chatbots can adapt their language use to the conversational context and the interlocutor's expectations.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
- cites Hill et al., 2015
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Corti and Gillespie (2016) show that people exert more effort toward establishing common ground with the agent when they are represented as fully human.
“in the context of general-purpose interactions, Corti and Gillespie (2016) show that people exert more effort toward establishing common ground with the agent when they are represented as fully human”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Corti and Gillespie (2016)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Proactivity influences perceived personality.
“According to the surveyed literature, proactivity influences perceived personality (P1) (Thies et al., 2017), since recommending and initiating topics may manifest higher levels of extraversion.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Araujo (2018) showed that using human-like language style, name, and greetings resulted in significantly higher scores for naturalness.
“Araujo (2018) showed that using human-like language style, name, and greetings resulted in significantly higher scores for naturalness.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Araujo (2018)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Conscientiousness influences the perceived personality.
“Conscientiousness is itself a dimension of the Big Five model; hence, conscientiousness influences the perceived personality (P5) (Goldberg, 1990).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Goldberg, 1990
Not checked in the free run.
- Interpretationcitation§ 3.3.2. Personality
Attributing personality to a chatbot increases believability.
“[B1] to increase believability: Morris (2002) states that chatbots should have a personality , defined by the Five Factor model, plus characteristics such as temperament and tolerance, in order to build utterances using linguistic choices that cohere with these attributions.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Morris (2002)
Not checked in the free run.
- cites Ptaszynski et al. (2010)
Not checked in the free run.
- cites Portela and Granell-Canut (2017)
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
When the context requires dynamic variation, thoroughness may reveal traits of the chatbot's identity.
“When the context requires dynamic variation (Gnewuch et al., 2017; Thies et al., 2017), thoroughness may reveal traits of the chatbot's identity (P16) (Marino, 2014; Schlesinger et al., 2018).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Marino, 2014
Not checked in the free run.
- cites Schlesinger et al., 2018
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Emotional intelligence improves perceived manners.
“Emotional intelligence improves perceived manners (P12) , since the lack of emotional intelligence may lead to the perception of impoliteness (Jenkins et al., 2007).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jenkins et al., 2007
Not checked in the free run.
- Interpretationcitation§ 4.3. Interrelationships among the characteristics
Personalization improves emotional intelligence.
“Personalization also improves emotional intelligence (P11) , since a chatbot should dynamically regulate the affective reactions to the interlocutor (Shum et al., 2018; Thies et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Shum et al., 2018
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- Premisecitation§ 4.1. A note on chatbots' humanness
In interactions with chatbots, the artificial agent represents the social role usually associated with a human.
“In interactions with chatbots, the artificial agent represents the social role usually associated with a human, for example, a tutor (Dyke et al., 2013; Tegos et al., 2016), a healthcare provider (Montenegro, da Costa, & da Rosa Righi, 2019), a salesperson (Gnewuch et al., 2017; Zhu, Zhang, Li, Huang, & Zhao, 2018), a hotel concierge (Lasek & Jessa, 2013), or even a friend (Shum et al., 2018; Thie”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Dyke et al., 2013
Not checked in the free run.
- cites Tegos et al., 2016
Not checked in the free run.
- cites Montenegro, da Costa, & da Rosa Righi, 2019
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
Sense of humor is highly shaped by cultural environment.
“[C1] to adapt humor to the users' culture: sense of humor is highly shaped by cultural environment (Ruch, 1998).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Ruch, 1998
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
Ptaszynski et al. (2010) found that the humorous chatbot scored significantly higher in naturalness and human-likeness compared to a non-humorous chatbot.
“When evaluating a humorous chatbot, Ptaszynski et al. (2010) compared the naturalness of the chatbot's inputs and the chatbot's human-likeness compared to a non-humorous chatbot. The humorous chatbot scored significantly higher in both constructs.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ptaszynski et al. (2010)
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
In Brandtzaeg and Følstad (2017), the second most frequent motivation for using chatbots, noted by 20% of the participants, was entertainment.
“In Brandtzaeg and Følstad (2017), the second most frequent motivation for using chatbots, noted by 20% of the participants, was entertainment.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Brandtzaeg and Følstad (2017)
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
Mairesse and Walker (2009) demonstrated that manipulating language to manifest a target personality produced moderately natural utterances, with a mean rating of 4.59 out of 7 for the personality model utterances.
“Mairesse and Walker (2009) demonstrated that manipulating language to manifest a target personality produced moderately natural utterances, with a mean rating of 4.59 out of 7 for the personality model utterances.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mairesse and Walker (2009)
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
The Big Five model can be assessed using validated psychological instruments.
“The Big Five model is a relevant tool because it can be assessed using validated psychological instruments (McCrae & Costa Jr, 1987).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites McCrae & Costa Jr, 1987
Not checked in the free run.
- Premisecitation§ 3.3.1. Identity
Overly humanized agents create a higher expectation for users, which eventually leads to more frustration when the chatbot fails.
“Overly humanized agents create a higher expectation for users, which eventually leads to more frustration when the chatbot fails (Gnewuch et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
- Premisecitation§ 4.1. A note on chatbots' humanness
Previous studies have shown that developing overly humanized agents results in high expectations and uncanny feelings.
“On the other hand, previous studies have also shown that developing overly humanized agents results in high expectations and uncanny feelings (Ciechanowski et al., 2018; Gnewuch et al., 2017), which was also pointed out in the surveyed literature as a challenge to conveying particular characteristics, such as identity and personality .”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Ciechanowski et al., 2018
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
- Premisecitation§ 3.3.2. Personality
Chatbots with consistent personality are more predictable and trustworthy.
“Chatbots with consistent personality are more predictable and trustworthy (Shum et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al., 2018
Not checked in the free run.
- Premisecitation§ 4.1. A note on chatbots' humanness
Interactivity is dependent on the identity of the source with whom/which we are carrying out the message exchange.
“An explanation for these contrasts is that interactivity is 'dependent on the identity of the source with whom/which we are carrying out the message exchange' (Sundar et al., 2016), i.e., people direct their messages to an artificial agent.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Sundar et al., 2016
Not checked in the free run.
- Classified as probably not a substantial claim. 213
- May combine two claims. 108
- The quote only partly states this claim. 2
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingown data§ 2. Overview of the surveyed literatureThe most representative specific domain is education, with 9 papers, followed by customer services, with 5 papers.
“The most representative specific domain is education, with 9 papers, followed by customer services, with 5 papers.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureMost surveyed studies adopted real chatbots (35 out of 56).
“Most surveyed studies adopted real chatbots (35 out of 56);”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureMost of the selected studies are recent publications (less than 10 years old).
“Most of the selected studies are recent publications (less than 10 years old).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given§ 1. IntroductionThe survey stated 22 propositions about how social characteristics may influence one another.
“We stated 22 propositions about how social characteristics may influence one another.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureGeneral purpose chatbots reflect 33% of the surveyed studies.
“General purpose chatbots reflect 33% of the surveyed studies.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingown data§ 2. Overview of the surveyed literatureThe publication venues include human-computer interactions (25 papers), learning and education (8 papers), information and interactive systems (8 papers), virtual agents (5 papers), artificial intelligence (3 papers), and natural language processing (2 papers).
“The publication venues include the domains of human-computer interactions (25 papers), learning and education (8 papers), information and interactive systems (8 papers), virtual agents (5 papers), artificial intelligence (3 papers), and natural language processing (2 papers).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureMost general purpose chatbots (16 out of 19) are designed to handle topic-unrestricted conversations.
“Most general purpose chatbots (16 out of 19) are designed to handle topic-unrestricted conversations.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingown data§ 3.1. Conversational IntelligenceOnly five studies applied only quantitative methods, while seven focused on qualitative methods.
“Only five studies applied only quantitative methods, while seven focused on qualitative methods.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3. Chatbots Social CharacteristicsSocial intelligence focuses on habitual social protocols.
“Social intelligence focuses on habitual social protocols, while personification refers to the chatbot's perceived identity and personality representations.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3. Chatbots Social CharacteristicsPersonification refers to the chatbot's perceived identity and personality representations.
“Social intelligence focuses on habitual social protocols, while personification refers to the chatbot's perceived identity and personality representations.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given§ 3.1. Conversational IntelligenceThe questionnaires are mostly Likert-scales, and some of them include subjective feedback.
“The questionnaires are mostly Likert-scales, and some of them include subjective feedback.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingnone given§ 3.1. Conversational IntelligenceThe social characteristics related to conversational intelligence are proactivity (18 studies), conscientiousness (11 studies), and communicability (6 studies).
“In this section, we discuss social characteristics related to conversational intelligence , namely: proactivity (18 studies), conscientiousness (11 studies), and communicability (6 studies).”
Quote in the paperNot a substantial claimMay combine two claims.
Findingcitation§ 3.1.1. ProactivityIn most of the studies, proactivity emerged either as an exploratory result, mostly from post-intervention interviews and user's feedback, or as a strategy to attend to domain-specific requirements.
“In most of the studies, however, proactivity emerged either as an exploratory result, mostly from post-intervention interviews and user's feedback (Duijvelshoff, 2017; Jain, Kumar, et al., 2018; Morrissey & Kirakowski, 2013; Portela & Granell-Canut, 2017; Shum et al., 2018; Thies et al., 2017), or as a strategy to attend to domain-specific requirements (e.g., monitoring, and guidance) (K. K. Fitzp”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijvelshoff, 2017
Not checked in the free run.
- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
Classified as probably not a substantial claim.
Findingnone given§ 2. Overview of the surveyed literatureFor each characteristic, the paper points out the benefits, challenges, and strategies of implementing the characteristic in chatbots as reported in the literature.
“For each characteristic, we point out the benefits, challenges, and strategies of implementing the characteristic in chatbots as reported in the literature.”
Quote in the paperSubstantial claimMay combine two claims.
Findingnone given§ 3.1.1. ProactivityIn task-oriented domains, some characteristics are largely influenced by the topic (e.g., Moral agency and Personality), while others are more generally applied (e.g., Manners and Damage control).
“In he task-oriented domains, some characteristics are largely influenced by the topic (e.g., Moral agency and Personality ), while others are more generally applied (e.g., Manners and Damage control ).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingown data§ 2. Overview of the surveyed literatureWhen a chatbot was simulated (11 studies), Wizard of Oz (WoZ) is the most used technique (9 studies).
“When a chatbot was simulated (11 studies), Wizard of Oz (WoZ) is the most used technique (9 studies).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureEight studies do not address a particular chatbot.
“Eight studies do not address a particular chatbot.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given§ 3.1. Conversational IntelligenceMost studies analyzed the interaction with real chatbots, although Wizard of Oz (WoZ) settings are also common.
“Most studies analyzed the interaction with real chatbots, although Wizard of Oz (WoZ) settings are also common.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation§ 3.1. Conversational IntelligenceOnly two papers did not evaluate a particular type of interaction because they were based on a literature review and surveys with chatbot users in general.
“Only two papers did not evaluate a particular type of interaction because they were based on a literature review (Gnewuch et al., 2017) and surveys with chatbot users in general (Brandtzaeg & Følstad, 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
- cites Brandtzaeg & Følstad, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 2. Overview of the surveyed literatureNine studies introduce a self-developed architecture and/or dialogue management.
“Nine studies introduce a selfdeveloped architecture and/or dialogue management (e.g. Dohsaka, Asai, Higashinaka, Minami, and Maeda (2014); Kumar, Ai, Beuth, and Ros´ e (2010)).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Dohsaka et al. (2014)
Not checked in the free run.
- cites Kumar et al. (2010)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingreasoning§ 3.1. Conversational IntelligenceThe majority of the studies (15) applied mixed methods (both quantitative and qualitative).
“The majority of the studies (15) applied mixed methods (both quantitative and qualitative).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation§ 2. Overview of the surveyed literatureIn another nine studies, the chatbots were designed for research purposes using third-party platforms for chatbot development and deployment, such as IBM's Watson service and Microsoft's Bot Framework as well as pattern-matching packages such as Artificial Intelligence Markup Language (AIML).
“In another nine studies, the chatbots were designed for research purposes using third-party platforms for chatbot development and deployment, such as IBM's Watson service (e.g., Q. V. Liao et al. (2018)) and Microsoft's Bot Framework (Toxtli et al., 2018) as well as patternmatching packages such as Artificial Intelligence Markup Language (AIML) (Silvervarg & J¨ onsson, 2013).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Q. V. Liao et al. (2018)
Not checked in the free run.
- cites Toxtli et al., 2018
Not checked in the free run.
- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3. Chatbots Social CharacteristicsThe category conversational intelligence includes characteristics that help the chatbot manage interactions.
“As Table 1 depicts, the category conversational intelligence includes characteristics that help the chatbot manage interactions.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 2. Overview of the surveyed literatureThe survey derived a total of 11 social characteristics and grouped them into three categories: conversational intelligence, social intelligence, and personification.
“We derived a total of 11 social characteristics, and grouped them into three categories, as depicted in Table 1: conversational intelligence , social intelligence , and personification .”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3. Chatbots Social CharacteristicsThe supplementary materials highlight five constructs that can be used to assess whether social characteristics reach the intended design goals.
“Finally, the supplementary materials also highlight five constructs that can be used to assess whether social characteristics reach the intended design goals.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 3. Chatbots Social CharacteristicsThe social characteristics were also grouped based on the domain in which they were investigated.
“We also grouped the social characteristics based on the domain in which they were investigated (Table 2).”
Quote in the paperNot a substantial claimMay combine two claims.
Findingreasoning§ 3.1.3. CommunicabilityWe did not identify studies on open domain chatbots that report on communicability, since in open domain interactions users are free to talk about varying topics and guidance is less a concern.
“We did not identify studies on open domain chatbots that report on communicability , since in open domain interactions users are free to talk about varying topics and guidance is less a concern.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 3.2. Social Intelligence16 studies reported both qualitative and quantitative results.
“16 studies reported both qualitative and quantitative results.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingown data§ 3.2. Social IntelligenceRegarding adopted research methods, 12 studies applied qualitative methods and 10 focused on quantitative methods.
“Regarding the adopted research methods, 12 studies applied qualitative methods and 10 focuses on quantitative methods.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 3.2.1. Damage controlDamage control was mostly investigated for open domain (two studies) and customer service chatbots (three studies).
“Damage control was mostly investigated for open domain (two studies) and customer service chatbots (three studies).”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 3.2.5. Emotional IntelligenceOnly three papers highlighted emotional intelligence as an exploratory outcome, where needs emerged from participants' subjective feedback and post-intervention surveys.
“Only three papers highlighted emotional intelligence as an exploratory outcome (Jenkins et al., 2007; Thies et al., 2017; Zamora, 2017), where needs for emotional intelligence emerged from participants' subjective feedback and post-intervention surveys.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Jenkins et al., 2007
Not checked in the free run.
- cites Thies et al., 2017
Not checked in the free run.
- cites Zamora, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Findingnone given§ 3.2.5. Emotional IntelligenceThe literature shows that emotional intelligence is widely investigated, with particular interest from education and mental health care domains.
“The literature shows that emotional intelligence is widely investigated, with particular interest from education and mental health care domains.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3.3.1. IdentityChatbots may have anthropomorphic, zoomorphic, or robotic representations.
“Additionally, chatbots may have anthropomorphic, zoomorphic, or robotic representations.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Findingreasoning§ actions:The social intelligence category includes characteristics that help a chatbot manifest adequate social behavior, by managing conflicts, using appropriate language, displaying manners and moral agency, sharing emotions, and handling personalized interactions.
“In summary, the social intelligence category includes characteristics that help a chatbot to manifest an adequate social behavior, by managing conflicts, using appropriate language, displaying manners and moral agency , sharing emotions, and handling personalized interactions.”
Quote in the paperSubstantial claimMay combine two claims.
Findingown data§ 3.3.1. IdentityThe survey found 16 studies that discuss identity issues, ten of which include identity as part of their main investigation.
“We found 16 studies that discuss identity issues, ten of which include identity as part of their main investigation (Araujo, 2018; Candello et al., 2017; Ciechanowski et al., 2018; Corti & Gillespie, 2016; De Angeli & Brahnam, 2006; De Angeli, Johnson, & Coventry, 2001; Jenkins et al., 2007; Q. V. Liao et al., 2018; Marino, 2014; Schlesinger et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Araujo, 2018
Not checked in the free run.
- cites Candello et al., 2017
Not checked in the free run.
- cites Ciechanowski et al., 2018
Not checked in the free run.
May combine two claims.
Findingown data§ 3.3. PersonificationSix studies applied quantitative methods, whereas the majority reported qualitative (10) or mixed (11) methods.
“Six studies applied quantitative methods, whereas the majority reported qualitative (10) or mixed (11) methods.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Findingnone given§ 3.3.1. IdentityOther domains include race-talk, education, and gaming.
“Other domains include race-talk, education, and gaming.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation§ 3.3.1. IdentityIn two studies, authors argue for impact of identity on interaction based on literature.
“In two studies, the authors argue for the impact of identity on the interaction based on the literature (Brandtzaeg & Følstad, 2018; Gnewuch et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Brandtzaeg & Følstad, 2018
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Findingcitation§ 3.3.1. IdentitySome authors include identity aspects in the definition of personality.
“Some authors include identity aspects in the definition of personality (see, e.g., Shum et al. (2018)).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
May combine two claims.
Findingreasoning§ actions:The benefits relate to resolving social positioning and recovering from failures, as well as increasing believability, human-likeness, engagement, and rapport.
“The benefits relate to resolving social positioning and recovering from failures, as well as increasing believability, human-likeness, engagement, and rapport.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 3.3. PersonificationIn this category, the survey found several studies where part of the main investigation relates to social characteristics.
“In this category, we found several studies where part of the main investigation relates to the social characteristics.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingnone given§ 3.3.1. IdentityAspects that convey chatbots' identity include gender, age, language style, and name.
“Aspects that convey the chatbots' identity include gender, age, language style, and name.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingown data§ 3.3. PersonificationThe survey divided social characteristics that reflect personification into identity (16 papers) and personality (12 papers).
“In this section, we divided the social characteristics that reflect personification into identity (16 papers) and personality (12 papers).”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 7. ConclusionSome characteristics are largely influenced by the domain (e.g., moral agency and communicability), while others are more generally applied (e.g., manners and damage control).
“We showed that some characteristics are largely influenced by the domain (e.g., moral agency and communicability ), while others are more generally applied (e.g., manners and damage control ).”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Findingreasoning§ 4.2. The importance of conversational contextPersonalization mostly co-occurs with proactivity.
“Noticeably, personalization mostly co-occurs with proactivity, since users expects proactive messages to be relevant to their particular interactional context.”
Quote in the paperNot a substantial claimMay combine two claims.
Findingown data§ 4.2. The importance of conversational contextMoral agency was reported only in race-talk, and open domain.
“It was reported only in race-talk, and open domain.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim. May combine two claims.
Study design and conductreasoning§ 2. Overview of the surveyed literatureThe survey decided not to include terms that relate to social characteristics/traits, because most studies do not explicitly label their results as such.
“We decided to not include terms that relate to social characteristics/traits, because most studies do not explicitly label their results as such.”
Quote in the paperSubstantial claim- Rests on an assumption: Most studies do not explicitly label their results as social characteristics/traits.
Classified as probably not a substantial claim.
Premisecitation§ 1. IntroductionMaking a conversational agent acceptable to users is primarily a social, not only technical, problem.
“Neururer and colleagues (2018) state that making a conversational agent acceptable to users is primarily a social, not only technical, problem.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Neururer et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 1. IntroductionChatbots are changing the patterns of interactions between humans and computers.
“Chatbots are changing the patterns of interactions between humans and computers (Følstad & Brandtzæg, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Følstad & Brandtzæg, 2017
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductreasoning§ 2. Overview of the surveyed literatureThe survey did not include 'personal assistants', since this term consistently refers to commercially available, voice-based assistants such as Google Assistant, Amazon's Alexa, Apple's Siri, and Microsoft's Cortana.
“We did not include 'personal assistants' either, since this term consistently refers to commercially available, voice-based assistants such as Google Assistant, Amazon's Alexa, Apple's Siri, and Microsoft's Cortana.”
Quote in the paperSubstantial claimMay combine two claims.
Premisecitation§ 1. IntroductionMost studies focus on a single or small set of characteristics; in other studies, the social characteristics emerged as secondary, exploratory results.
“However, most studies focus on a single or small set of characteristics (e.g., Mairesse and Walker (2009); Schlesinger, O'Hara, and Taylor (2018)); in other studies, the social characteristics emerged as secondary, exploratory results (e.g., Tallyn, Fried, Gianni, Isard, and Speed (2018); Toxtli, Cranshaw, et al. (2018)).”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Mairesse and Walker (2009)
Not checked in the free run.
- cites Schlesinger, O'Hara, and Taylor (2018)
Not checked in the free run.
- cites Tallyn et al. (2018)
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ 1. IntroductionIt has become difficult to find evidence regarding what characteristics are important for designing a particular chatbot, and what research opportunities exist in the field.
“It has become difficult to find evidence regarding what characteristics are important for designing a particular chatbot, and what research opportunities exist in the field.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductown data§ 2. Overview of the surveyed literatureTo find relevant studies, the survey used a search string that includes the synonyms 'chatbots, chatterbots, conversational agents, conversational interfaces, conversational systems, conversation systems, dialogue systems, digital assistants, intelligent assistants, conversational user interfaces, and conversational UI'.
“to find relevant studies we used a search string that includes the synonyms 'chatbots, chatterbots, conversational agents, conversational interfaces, conversational systems, conversation systems, dialogue systems, digital assistants, intelligent assistants, conversational user interfaces, and conversational UI' .”
Quote in the paperSubstantial claim- Rests on an assumption: The literature presents no coherent definition of chatbots.
Classified as probably not a substantial claim. May combine two claims.
Study design and conductnone given§ 2. Overview of the surveyed literatureAfter reading the full texts, papers that either did not highlight social characteristics or represented previous, ongoing research of another complete study from the same authors were removed.
“After reading the full texts, we removed the papers that either did not highlight social characteristics or represented previous, ongoing research of another complete study from the same authors.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductown data§ 2. Overview of the surveyed literatureAfter filtering the search results, 56 studies remained.
“After filtering the search results, we had 56 remaining studies.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductcitation§ 2. Overview of the surveyed literatureThe datasets with all analyzed studies (original list of results and exclusions per round) are available in Chaves and Gerosa (2019).
“The datasets with all analyzed studies (original list of results and exclusions per round) is available in Chaves and Gerosa (2019).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Chaves and Gerosa (2019)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductown data§ 2. Overview of the surveyed literatureThe search started with a set of about one thousand papers.
“We started with a set of about one thousand papers.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 1. IntroductionDesigning overly humanized agents results in uncanny feelings and increased expectations, which also negatively impacts the interaction.
“In contrast, designing overly humanized agents results in uncanny feelings and increased expectations (Ciechanowski, Przegalinska, Magnuski, & Gloor, 2018; Gnewuch et al., 2017), which also negatively impacts the interaction.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Ciechanowski, Przegalinska, Magnuski, & Gloor, 2018
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
Classified as probably not a substantial claim. May combine two claims.
Study design and conductcitation§ 2. Overview of the surveyed literatureThe search string did not include the term 'social bots', because it refers to chatbots that produce content for social networks such as Twitter.
“The search string did not include the term 'social bots', because it refers to chatbots that produce content for social networks such as Twitter (Ferrara, Varol, Davis, Menczer, & Flammini, 2016).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Ferrara, Varol, Davis, Menczer, & Flammini, 2016
Not checked in the free run.
Classified as probably not a substantial claim.
Premisecitation§ 1. IntroductionAs chatbots are designed to interact with users in a way that mimics person-to-person conversations, new challenges in HCI arise.
“As chatbots are designed to interact with users in a way that mimics person-to-person conversations, new challenges in HCI arise (Følstad & Brandtzæg, 2017; Nguyen & Sidorova, 2018).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Følstad & Brandtzæg, 2017
Not checked in the free run.
- cites Nguyen & Sidorova, 2018
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductown data§ 2. Overview of the surveyed literatureTo find studies from a variety of domains (not only computing), the survey used Google Scholar to search for papers.
“Additionally, to find studies from a variety of domains (not only computing), we used Google Scholar to search for papers.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductown data§ 2. Overview of the surveyed literatureThe second round started with 464 studies.
“We started the second round with 464 studies.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductnone given§ 2. Overview of the surveyed literatureIn the second round, short/position papers, theses, book chapters, and documents published in non-scientific venues were excluded.
“In this round, we excluded short/position papers, theses, book chapters, and documents published in non-scientific venues.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductown data§ 2. Overview of the surveyed literatureThe third and last round started with 104 papers.
“The third and last round started with 104 papers.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim. May combine two claims.
Study design and conductnone given§ 2. Overview of the surveyed literatureThe survey explicitly left out studies that relate to embodiment ('ECA, multimodal, robots, eye-gaze, gesture') and speech input mode ('speech-based, speech-recognition, voice-based').
“We explicitly left out studies that relate to embodiment ( 'ECA, multimodal, robots, eye-gaze, gesture' ), and speech input mode ( 'speech-based, speech-recognition, voice-based' ).”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductnone given§ 2. Overview of the surveyed literaturePapers for which full text was not available or written in a language other than English were removed.
“We also removed papers for which full text was not available or written in a language other than English.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductown data§ 2. Overview of the surveyed literatureIn the first round, the amount was reduced by about half based on the titles.
“In the first round, we reduced this amount by about half based on the titles.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S2 (checkable), S4 (based).
Interpretationnone given§ ABSTRACTEnriching chatbots with social characteristics that cohere with users' expectations avoids frustration and dissatisfaction.
“In this survey, we argue that chatbots should be enriched with social characteristics that cohere with users' expectations, ultimately avoiding frustration and dissatisfaction.”
Quote in the paperNot a substantial claim- Rests on an assumption: The increasing need to approximate conversational interaction styles raises users' expectations that chatbots present social behaviors habitual in human-human communication.
Classified as probably not a substantial claim.
Study design and conductnone given§ 2. Overview of the surveyed literatureAbstracts were read and all papers that focused on technical aspects rather than social ones were removed.
“We also read the abstracts and removed all the papers that focused on technical aspects, rather than social ones.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim. May combine two claims.
Study design and conductown data§ 2. Overview of the surveyed literatureAfter coding all the studies, a second researcher (the second author) reviewed the produced set of characteristics and both researchers participated in discussion sessions to identify characteristics that could be merged, renamed, or removed.
“After coding all the studies, a second researcher (the second author) reviewed the produced set of characteristics and both researchers participated in discussion sessions to identify characteristics that could be merged, renamed, or removed.”
Quote in the paperSubstantial claimClassified as probably not a substantial claim.
Study design and conductown data§ 2. Overview of the surveyed literatureAt the end, the characteristics were grouped into categories depending on whether the characteristic relates to the chatbot's virtual representation, conversational behavior, or social protocols.
“At the end, the characteristics were grouped into the categories, depending on whether the characteristic relates to the chatbot's virtual representation, conversational behavior, or social protocols.”
Quote in the paperSubstantial claimMay combine two claims.
Premisecitation§ 3.1.1. ProactivityProactively suggesting and encouraging new topics have been shown useful to inspire users and keep the conversation alive.
“proactively suggesting and encouraging new topics have been shown useful to both inspire users (Avula et al., 2018; Chaves & Gerosa, 2018) and keep the conversation alive (Silvervarg & J¨ onsson, 2013).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Avula et al., 2018
Not checked in the free run.
- cites Chaves & Gerosa, 2018
Not checked in the free run.
- cites Silvervarg & J¨ onsson, 2013
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductown data§ 2. Overview of the surveyed literatureThe papers were analyzed by searching for chatbot behavior or attributed characteristics that influence the way users perceive it and behave toward it.
“We analyzed the papers by searching for chatbot behavior or attributed characteristics that influence the way users perceive it and behave toward it.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductnone given§ 2. Overview of the surveyed literatureThese steps were performed by one researcher (the first author).
“These steps were performed by one researcher (the first author).”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductnone given§ 2. Overview of the surveyed literatureFinally, the quotes for each characteristic were labeled as references to benefits, challenges, or strategies.
“Finally, the quotes for each characteristic were labeled as references to benefits, challenges, or strategies.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim.
Study design and conductown data§ 2. Overview of the surveyed literatureFor each study (document), relevant statements from the paper (quotes) were selected and labeled as a characteristic (code).
“For each study ( document ), we selected relevant statements from the paper ( quotes ) and labeled them as a characteristic ( code ).”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.1. ProactivityIn human-chatbot conversations, a proactive behavior enables a chatbot to share initiative with the user, contributing to the conversation in a more natural way.
“In human-chatbot conversations, a proactive behavior enables a chatbot to share initiative with the user, contributing to the conversation in a more natural way (Morrissey & Kirakowski, 2013).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessFor complex tasks, to keep the conversation on track the user must be aware of the next steps or why something is happening.
“The authors found that, for complex tasks, to keep the conversation on track the user must be aware of the next steps or why something is happening.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessComfortably conversing on any topic related to the service offering is a requirement for task-oriented chatbots.
“based on the literature on customer support chatbots, Gnewuch et al. (2017) argue that comfortably conversing on any topic related to the service offering is a requirement for task-oriented chatbots.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessIn task-oriented interactions, a chatbot should understand the purpose of the interaction and strive to conduct the conversation toward this goal in an efficient, productive way.
“in taskoriented interactions, a chatbot should understand the purpose of the interaction and strive to conduct the conversation toward this goal in an efficient, productive way (Ayedoun et al., 2017; Duijst, 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Ayedoun et al., 2017
Not checked in the free run.
- cites Duijst, 2017
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessMost chatbots in the second language field cannot hold continuous conversations, since they are developed to answer the user's last input; therefore, they did not have the sense of topic, which resulted in instances of inappropriate response.
“Coniam (2008) reviewed popular chatbots for practicing second languages. The author showed that most chatbots in this field cannot hold continuous conversations, since they are developed to answer the user's last input. Therefore, they did not have the sense of topic, which resulted in instances of inappropriate response.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Coniam, 2008
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessMaintaining a theme is convincing, while failure to do so is unconvincing.
“When evaluating the naturalness of a chatbot, Morrissey and Kirakowski (2013) found that maintaining a theme is convincing, while failure to do so is unconvincing.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessProductivity is the key motivating factor for using chatbots (68% of the participants mentioned it as the main reason for using chatbots).
“Brandtzaeg and Følstad (2017) show that productivity is the key motivating factor for using chatbots (68% of the participants mentioned it as the main reason for using chatbots).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Brandtzaeg & Følstad, 2017
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ 3.1.2. ConscientiousnessThe chatbot's attentiveness to the interactional goal may not be evident to the user if the chatbot passively waits for the user to control the interaction; thus, conscientiousness relates to proactive ability.
“the chatbot's attentiveness to the interactional goal may not be evident to the user if the chatbot passively waits for the user to control the interaction. Thus, conscientiousness relates to proactive ability, as discussed in Section 3.1.1.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessAs the complexity of tasks increases, more turns are required to achieve a goal; hence, more mistakes may be made.
“as the complexity of tasks increases, more turns are required to achieve a goal; hence, more mistakes may be made. This argument was supported by both Duijst (2017) and Dyke et al. (2013)”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Dyke et al., 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessConscientiousness enables a chatbot to follow the conversational flow, show understanding of the context, and interpret each utterance as a meaningful part of the whole conversation.
“It enables a chatbot to follow the conversational flow, show understanding of the context, and interpret each utterance as a meaningful part of the whole conversation (Morrissey & Kirakowski, 2013).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Morrissey & Kirakowski, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessA conversation with a chatbot should maintain a 'sense of continuity over time' to demonstrate that the chatbot is exerting effort to track the conversation.
“a conversation with a chatbot should maintain a ' sense of continuity over time ' (Jain, Kumar, et al., 2018) to demonstrate that the chatbot is exerting effort to track the conversation.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationreasoning§ 3.1.1. ProactivityContextualized proactive interventions suggest that the chatbot should be attentive to the conversation, which conveys conscientiousness.
“Contextualized proactive interventions also suggest that the chatbot should be attentive to the conversation, which conveys conscientiousness , as discussed in the next section.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.1.1. ProactivityPrivacy concerns may result in under-motivated users, discomfort about disclosing information, and lack of engagement.
“Privacy concerns may result in under-motivated users, discomfort about disclosing information, and lack of engagement (Duijvelshoff, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijvelshoff, 2017
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessWhen a chatbot does not interpret the meaning of users' utterances, users show frustration and the chatbot's credibility is compromised.
“As shown by Duijst (2017), when a chatbot does not interpret the meaning of users' utterances, users show frustration and the chatbot's credibility is compromised.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst, 2017
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessChatbots are designed to restrict free-text inputs from the user to ensure the conversational structure and to hide natural language limitations.
“aiming to ensure the conversational structureand to hide natural language limitations-chatbots are designed to restrict free-text inputs from the user (Duijst, 2017; Jain, Kumar, et al., 2018; Tallyn et al., 2018).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Duijst, 2017
Not checked in the free run.
- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Tallyn et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessThe user and chatbot should be on the same page about the chatbot's contextual state, providing the users the opportunity to clarify possible misunderstandings.
“In both cases, the user and chatbot should be on the same page about the chatbot's contextual state (Jain, Kota, et al., 2018), providing the users the opportunity to clarify possible misunderstandings (Gnewuch et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jain, Kota, et al., 2018
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessA chatbot should provide a way to inform the user of the current context, especially for complex tasks.
“a chatbot should provide a way to inform the user of the current context, especially for complex tasks.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jain, Kota, et al., 2018
Not checked in the free run.
- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.1. ProactivityOne surveyed paper proposes a chatbot that selects a topic randomly but also observes that the lack of context is a major problem of this approach.
“One surveyed paper (Portela & Granell-Canut, 2017) proposes a chatbot that [S2] selects a topic randomly but also observes that the lack of context is a major problem of this approach.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Portela & Granell-Canut, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Premisecitation§ 3.2. Social IntelligenceChatbots should be able to respond to social cues, accept differences, manage conflicts, be empathic, and demonstrate caring.
“Chatbots should be able to respond to social cues during the conversation, accept differences, and manage conflicts (Salovey & Mayer, 1990) as well as be empathic and demonstrate caring (Bj¨ orkqvist et al., 2000)”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Salovey & Mayer, 1990
Not checked in the free run.
- cites Björkqvist et al., 2000
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityProviding communicability helps users to interpret the codes used by designers to convey the interactional possibilities embedded in the software, which improves system learnability.
“Providing communicability helps users to interpret the codes used by designers to convey the interactional possibilities embedded in the software (De Souza, Prates, & Barbosa, 1999), which improves system learnability (Grossman, Fitzmaurice, & Attar, 2009).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites De Souza et al., 1999
Not checked in the free run.
- cites Grossman et al., 2009
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityWhen the chatbot is not able to answer the user, or when it notices that the user is silent, it may suggest available features to stimulate the user to engage.
“when the chatbot is not able to answer the user, or when it notices that the user is silent, it may suggest available features to stimulate the user to engage (Jain, Kumar, et al., 2018; Val´ erio et al., 2017).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Val´ erio et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityThe problem around chatbots' communicability lies in the nature of the interface: instead of buttons, menus, and links, chatbots unveil their capabilities through conversational turns, one sentence at a time.
“The problema around chatbots' communicability lies in the nature of the interface: instead of buttons, menus, and links, chatbots unveil their capabilities through conversational turns, one sentence at a time (Val´ erio et al., 2017)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityWhile interacting with chatbots, users may not know that a desired functionality is available or how to use it.
“while interacting with chatbots, users may not know that a desired functionality is available or how to use it (Jain, Kumar, et al., 2018; Val´ erio et al., 2017).”
Quote in the paperSubstantial claim0 of 2 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Val´ erio et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilitySystem learnability is the most fundamental component for usability.
“The literature on interactive systems has highlighted system learnability as the most fundamental component for usability (Grossman et al., 2009)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Grossman et al., 2009
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityChatbots should recognize a 'help' input from the user, so it can provide instructions on how to proceed.
“chatbots should recognize a 'help' input from the user, so it can provide instructions on how to proceed (Val´ erio et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.2. ConscientiousnessThe workflow should be flexible enough to handle both multi-turn and one-turn question-answer interactions; it also should be unambiguous, such that users can efficiently achieve their goals.
“Gnewuch et al. (2017) argue that the workflow should be flexible enough to handle both multi-turn and one-turn question-answer interactions; it also should be unambiguous, such that users can efficiently achieve their goals.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityInteractive software is communicative by its nature, since users achieve their goals by exchanging messages with the system.
“Interactive software is communicative by its nature, since users achieve their goals by exchanging messages with the system (Prates, de Souza, & Barbosa, 2000; Sundar, Bellur, Oh, Jia, & Kim, 2016).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Prates et al., 2000
Not checked in the free run.
- cites Sundar et al., 2016
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityCommunicating chatbots' functionalities should be performed as much as possible within the chat interface.
“communicating chatbots' functionalities should be performed as much as possible within the chat interface (Jain, Kumar, et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable).
Premisereasoning§ 3.2. Social IntelligenceWhen developing chatbots, it is necessary to account for socially acceptable protocols for conversational interactions.
“Hence, when developing chatbots, it is necessary to account for the socially acceptable protocols for conversational interactions (Walker, 2009; Wallis & Norling, 2005).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Walker, 2009
Not checked in the free run.
- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityChatbots should be able to answer ability-check questions.
“results from (Q. V. Liao et al., 2018) show that chatbots should be able to answer ability-check questions (e.g., ' what can you do? ' or ' can you do [functionality]? ').”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityThis inconsistency produces the user's feeling of misinterpreting the affordances, which has a negative impact on the system's learnability.
“This inconsistency produces the user's feeling of misinterpreting the affordances, which has a negative impact on the system's learnability.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Val´ erio et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ 3.1.2. ConscientiousnessWhen chatbots are built into third-party apps (e.g., Facebook Messenger), an extra window may not be possible.
“However, when the chatbots are built into third-party apps (e.g., Facebook Messenger), an extra window may not be possible.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2. Social IntelligenceThese abilities ultimately increase chatbots' authenticity.
“which ultimately increase chatbots' authenticity (Neururer et al., 2018)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Neururer et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityProviding an opening message with insights into the chatbots' capabilities is a requirement for chatbots design.
“The authors argue that providing an opening message with insights into the chatbots' capabilities is a requirement for chatbots design.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.2. ConscientiousnessDesigning a conversational blueprint helps to conduct the conversation strictly and productively to the goal.
“designing a conversational blueprint helps to conduct the conversation strictly and productively to the goal (Duijst, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityBusiness integration is a requirement for designing chatbots, so that the chatbot can solve the users' requests without transferring the interaction to another user interface.
“According to Gnewuch et al. (2017), business integration is a requirement for designing chatbots, so that the chatbot can solve the users' requests without transferring the interaction to another user interface.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ 3.1.3. CommunicabilityCommunicability may be used as a strategy to avoid mistakes (damage control).
“Communicability may also be used as a strategy to avoid mistakes ( damage control )”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.1.3. CommunicabilityA clarification about the chatbots' purpose should be placed in the introductory message.
“First-time users in Jain, Kumar, et al. (2018) highlighted that a clarification about the chatbots' purpose should be placed in the introductory message.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityWhen first-time users do not understand chatbots' capabilities and limitations, they have high expectations and, consequently, end up more frustrated when the chatbots fail.
“Jain, Kumar, et al. (2018) observed that when first-time users do not understand chatbots' capabilities and limitations, they have high expectations and, consequently, end up more frustrated when the chatbots fail.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
May combine two claims.
Premisenone given§ 3.1.2. ConscientiousnessMost of the results are exploratory; a lack of studies investigate the extent to which the provided strategies influence users' behaviors and perceptions.
“However, most of the results are exploratory; a lack of studies investigate the extent to which the provided strategies influence users' behaviors and perceptions.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation§ 3.1.3. CommunicabilityAn easy-to-learn system should lead the user to perform well, even during their initial interactions.
“an easy-to-learn system should lead the user to perform well, even during their initial interactions”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.1.3. CommunicabilityAbility-check questions helped users to understand the system and reduce uncertainty.
“According to the authors, ability-check questions helped users to understand the system and reduce uncertainty (Q. V. Liao et al., 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2. Social IntelligenceIn HCI, Media Equation theory posits that people react to computers as social actors.
“In the HCI domain, the Media Equation theory (Reeves & Nass, 1996) posits that people react to computers as social actors.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Reeves & Nass, 1996
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlDialogue-reference errors are one of the major reasons for failed dialogues and they mostly result from chatbots' misunderstandings.
“dialogue-reference errors (e.g., user's attempt to correct a previous answer or jumping back to an earlier question) are one of the major reasons for failed dialogues and they mostly result from chatbots' misunderstandings”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mäurer & Weihe, 2015
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlChatbots often fail in a conversation due to lack of either linguistic or world knowledge.
“chatbots often fail in a conversation due to lack of either linguistic or world knowledge (Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.
Interpretationreasoning§ 3.2.1. Damage controlIt is necessary to enrich chatbots with the ability to recover from failures and handle inappropriate talk in a socially acceptable manner.
“Thus, it is necessary to enrich chatbots with the ability to recover from failures and handle inappropriate talk in a socially acceptable manner (Jain, Kumar, et al., 2018; Silvervarg & J¨ onsson, 2013; Wallis & Norling, 2005).”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlProviding damage control in chatbots has the benefit of dealing with testing.
“[B2] to deal with testing”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.2.1. Damage controlIn open domain interactions, users are free to wander among topics and testing or flaming tends to be more frequent.
“In open domain interactions, users are free to wander among topics and testing or flaming tends to be more frequent (Hill et al., 2015).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Hill et al., 2015
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlThe longer the conversations last, the more users are encouraged to go beyond the chatbot's main functions.
“Qualitative evaluation reveals that the longer the conversations last, the more users are encouraged to go beyond the chatbots main functions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlThe chatbot failed to answer 10% of the exchanged messages in a task management chatbot log.
“the chatbot failed to answer 10% of the exchanged messages”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Toxtli et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlUsers who want to test and find the system's borders are likely to never have a meaningful conversation with the chatbot no matter how sophisticated it is.
“users who want to test and find the system's borders are likely to never have a meaningful conversation with the chatbot no matter how sophisticated it is”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlAbout 4% of the conversations in the Amazon Alexa Prize 2017 corpus included sexually explicit utterances.
“the researchers estimated that about 4% of the conversations included sexually explicit utterances”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage control2.8% of all statements were abusive.
“2.8% of all statements were abusive”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlIn analyzing conversation logs from hotel chatbots, Lasek and Jessa (2013) observed that 4% of the conversations contained vulgar, indecent, and insulting vocabulary.
“When analyzing conversation logs from hotel chatbots, Lasek and Jessa (2013) observed that 4% of the conversations contained vulgar, indecent, and insulting vocabulary”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlCasually testing the chatbots' 'intelligence' is a manifestation of satisfaction seeking.
“casually testing the chatbots' 'intelligence' is a manifestation of satisfaction seeking”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlIn the customer services context, the chatbot needs to avoid disappointing the user, as frustration may negatively reflect the business that the agent represents.
“In the customer services context, the chatbot needs to avoid disappointing the user, as frustration may negatively reflect the business that the agent represents (Araujo, 2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Araujo, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlSexual expressions represented 1.8% of all statements.
“sexual expressions represented 1.8% of all statements”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Lasek & Jessa, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlHandling testing helps chatbots to establish limits and resolve social positioning.
“Wallis and Norling (2005) argue that handling this type of testing helps the chatbots to establish limits and resolve social positioning.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlDamage control enables the chatbot to admit the lack of knowledge or cover up cleverly.
“Damage control enables the chatbot to admit the lack of knowledge or cover up cleverly (Jain, Kumar, et al., 2018)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlA few interactions failed because the users' motivations were curiosity and mischief rather than trying to solve the decision problem.
“a few interactions failed because the users' motivations were curiosity and mischief rather than trying to solve the decision problem”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mäurer & Weihe, 2015
Not checked in the free run.
Classified as probably not a substantial claim.
Interpretationreasoning§ 3.2.1. Damage controlProviding means to identify an abusive utterance is important to adopting damage control strategies.
“Providing means to identify an abusive utterance is important to adopting damage control strategies.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ 3.2.1. Damage controlEnriching chatbots with the ability to choose between the options is a challenge.
“Enriching chatbots with the ability to choose between the options is a challenge.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.2.1. Damage controlThe most powerful conversational act that predicted user satisfaction was the agent ability-check questions and the explicit feedback #fail, although closings and off-topic requests were also significant in predicting frustration.
“The most powerful conversational act that predicted user satisfaction in that study was the agent ability-check questions, see discussion in Communicability section) and the explicit feedback #fail , although closings and off-topic requests were also significant in predicting frustration.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ 3.2.1. Damage controlSuccessfully implementing conscientiousness and communicability may prevent errors; hence, strategies to provide these characteristics can also be used for damage control.
“successfully implementing conscientiousness and communicability may prevent errors; hence, strategies to provide these characteristics can also be used for damage control”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.2.1. Damage controlBecause chatbots do not understand profanity or abuse, they may not recognize a statement as harassment, which makes it difficult to adopt answering strategies.
“Because they do not understand profanity or abuse, they may not recognize a statement as harassment, which makes it difficult to adopt answering strategies (Curry & Rieser, 2018).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage control42.4% of the users sent a '#fail' statement at least once, and the number of complaints and flaming for the proposed chatbot was significantly lower than the baseline.
“42.4% of the users did it at least once, and the number of complaints and flaming for the proposed chatbot was significantly lower than the baseline”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlBeing part of a recognized institution places the chatbot in a stronger social group.
“being part of a recognized institution places the chatbot in a stronger social group”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlChatbots could redirect users' problematic requests to a human attendant in order to avoid conflict situations.
“Toxtli et al. (2018) and Jenkins et al. (2007) also suggest that chatbots could redirect users' problematic requests to a human attendant in order to avoid conflict situations.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Toxtli et al., 2018
Not checked in the free run.
- cites Jenkins et al., 2007
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.1. Damage controlThe amount of implicit feedback was also significant, which advocates for predicting user's satisfaction from the conversation.
“However, the amount of implicit feedback was also significant, which advocates for predicting user's satisfaction from the conversation.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Q. V. Liao et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlChoosing between peaceful or aggressive reactions in conflict situations is optional for socially intelligent individuals.
“For Bj¨ orkqvist et al. (2000), choosing between peaceful or aggressive reactions in conflict situations is optional for socially intelligent individuals.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Björkqvist et al., 2000
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.1. Damage controlWhen facing testing or abuse, chatbots can communicate consequences or call on the authority of others.
“when facing testing or abuse, chatbots can communicate consequences (Silvervarg & J¨ onsson, 2013) or call on the authority of others (Toxtli et al., 2018; Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
- cites Toxtli et al., 2018
Not checked in the free run.
- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlIgnoring abuse and testing is not a good strategy because it could encourage more extreme behaviors.
“Wallis and Norling (2005) argue that ignoring abuse and testing is not a good strategy because it could encourage more extreme behaviors.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Classified as probably not a substantial claim. May combine two claims.
Premisecitation§ 3.2.1. Damage controlIgnoring abuse and testing positions the chatbot as an inferior individual, which is particularly harmful in scenarios where the chatbot should demonstrate a more prominent or authoritative social role.
“It also positions the chatbot as an inferior individual, which is particularly harmful in scenarios where the chatbot should demonstrate a more prominent or authoritative social role (e.g., a tutor).”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlWhen faced with abuse, a chatbot could be seen to take offense and respond in kind or act hurt.
“Wallis and Norling (2005) suggest that when faced with abuse, a chatbot could be seen to take offense and respond in kind or act hurt.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Interpretationreasoning§ 3.2.1. Damage controlDamage control strategies need to be adapted to both the social situation and the intensity of the conflict.
“Damage control strategies need to be adapted to both the social situation and the intensity of the conflict.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlWhen the chatbot is not accepted as part of the social group it represents, it is discredited by the user, leading the interaction to fail.
“Wallis and Norling (2005) argue that when the chatbot is not accepted as part of the social group it represents, it is discredited by the user, leading the interaction to fail.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlPosting confirmation messages avoids trapping the users in the wrong conversation path.
“Gnewuch et al. (2017) discuss that posting confirmation messages avoids trapping the users in the wrong conversation path.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Gnewuch et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ 3.2.1. Damage controlThe strategies can escalate in severity if the conflict is not solved.
“The strategies can escalate in severity if the conflict is not solved.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlAbusive behavior may lead the chatbot to stop responding until the student changes the topic.
“abusive behavior may lead the chatbot to stop responding until the student changes the topic”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Silvervarg & Jönsson, 2013
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlCurry and Rieser (2018) categorized responses from state-of-the-art conversational systems in a pool of emotional reactions, both positive and negative.
“Curry and Rieser (2018) categorized responses from state-of-the-art conversational systems in a pool of emotional reactions, both positive and negative.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlDeciding what strategy is adequate to the intensity of the conflict is crucial.
“Deciding what strategy is adequate to the intensity of the conflict is crucial (Wallis & Norling, 2005).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlHumans might feel inhibited about hurting the pretended feelings of a machine if the machine is willing to hurt a human's feelings too.
“humans might feel inhibited about hurting the pretended feelings of a machine if the machine is willing to hurt a human's feelings too (Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlDesigning chatbots with too strong of reactions may lead to ethical concerns.
“designing chatbots with too strong of reactions may lead to ethical concerns (Wallis & Norling, 2005)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlCooperative users are significantly more likely to give a higher rating for overall evaluation and decision efficiency.
“cooperative users are significantly more likely to give a higher rating for overall evaluation and decision efficiency”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mäurer & Weihe, 2015
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlHaving visual elements such as quick replies prevents errors, since they keep the users aware of what to ask and the chatbot is more likely to know how to respond.
“having visual elements such as quick replies prevents errors, since they keep the users aware of what to ask and the chatbot is more likely to know how to respond (Duijst, 2017)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ 3.2.1. Damage controlIn human-chatbot interactions, predicting users' behavior toward the chatbots in a specific context to develop the appropriate behavior is a challenge.
“In humanchatbot interactions, however, predicting users' behavior toward the chatbots in a specific context to develop the appropriate behavior is a challenge.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim. May combine two claims.
Premisecitation§ 3.2.1. Damage controlAccording to Wallis and Norling (2005), humans also fail in conversations; they misunderstand what their partner says and do not know things that are assumed common knowledge by others.
“According to Wallis and Norling (2005), humans also fail in conversations; they misunderstand what their partner says and do not know things that are assumed common knowledge by others.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlUsers appeared to be uncomfortable and annoyed whenever the chatbot pointed out any defect in the user or reacted to aggression, as this behavior conflicted with the user's perceived power relations.
“users appeared to be uncomfortable and annoyed whenever the chatbot pointed out any defect in the user or reacted to aggression, as this behavior conflicted with the user's perceived power relations”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli, Johnson, & Coventry, 2001
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlThe reactions include humorous responses, chastising and retaliation, and evasive responses, as well as flirtation and play-along utterances.
“The reactions include humorous responses, chastising and retaliation, and evasive responses, as well as flirtation and play-along utterances.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.1. Damage controlIf escalating the aggressive behavior is not appropriate, the chatbot could withdraw from the conversation to demonstrate that the user's behavior is not acceptable.
“If escalating the aggressive behavior is not appropriate, the chatbot could withdraw from the conversation (Wallis & Norling, 2005) to demonstrate that the user's behavior is not acceptable.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).
Interpretationnone given§ 3.2.1. Damage controlTo provide an emotional reaction, emotional intelligence is also required.
“To provide an emotional reaction, emotional intelligence is also required.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.1. Damage controlBeing evasive about sexual statements may convey the impression of flirtatiousness, which would not be an acceptable behavior for a customer assistant or a tutor chatbot.
“Curry and Rieser (2018) showed that being evasive about sexual statements may convey the impression of flirtatiousness, which would not be an acceptable behavior for a customer assistant or a tutor chatbot.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Curry & Rieser, 2018
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ 3.2.4. Moral agencyThe clean-data strategy does not manifest agency, but rather alienates the chatbot of the topic.
“Although this strategy is useful to prevent unwanted behavior, it does not manifest agency, but rather alienates the chatbot of the topic.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.2. ThoroughnessPeople use fewer words per message and a more limited vocabulary with chatbots.
“people use, indeed, fewer words per message and a more limited vocabulary with chatbots”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Hill et al., 2015
Not checked in the free run.
Classified as probably not a substantial claim.
Premisecitation§ 3.2.4. Moral agencyIn Banks (2018), all constructs (goodwill, trustworthiness, willingness to engage, and relational certainty) correlate with morality.
“Statistical results showed that all the constructs correlate with morality, which suggests that manifesting moral agency can enrich interpersonal relationships with chatbots.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites Banks (2018)
Not checked in the free run.
May combine two claims.
Interpretationown data§ 3.2.4. Moral agencyMoral agency is primarily relevant when the conversational topic may raise moral concerns, which ultimately requires ethical behavior from conversational partners.
“Moral agency was observed in only two domains of studies: open domain (four studies) and race-talk (two studies), which shows that this characteristic is primarily relevant when the conversational topic may raise moral concerns, which ultimately requires ethical behavior from the conversational partners.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.3. MannersCurrent online communication media has been successfully used to initiate, develop, and maintain interpersonal relationships.
“even so, current online communication media has been successfully used to initiate, develop, and maintain interpersonal relationships (Walther, 2011).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Walther, 2011
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.4. Moral agencyLack of understanding about sex-talk does not prevent the studied chatbot from harsh verbal abuse, or even from being perceived as encouraging such abuse.
“De Angeli and Brahnam (2006) show that the lack of understanding about sex-talk does not prevent the studied chatbot from harsh verbal abuse, or even from being perceived as encouraging such abuse.”
Quote in the paperSubstantial claim0 of 1 sources checked- cites De Angeli and Brahnam (2006)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.4. Moral agencyIn Shum et al. (2018), moral agency is discussed as a secondary result, where the authors discuss the impact of biased responses on emotional connection.
“In Shum et al. (2018), moral agency is discussed as a secondary result, where the authors discuss the impact of biased responses on emotional connection.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.4. Moral agencyText-based chatbots may also be assessed by their social representation, which risks building or reinforcing stereotypes.
“Although the chatbot's personification is more evident in embodied conversational agents, text-based chatbots may also be assessed by their social representation, which risks building or reinforcing stereotypes (Marino, 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Marino, 2014
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.3. MannersCMC is by itself more impersonal than face-to-face conversation.
“CMC is by itself more impersonal than face-to-face conversation (Walther, 1992, 1996);”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Walther, 1992, 1996
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.4. Moral agencySchlesinger et al. (2018) argue that lack of context about the world does not redeem the chatbot from the necessity of being respectful with all social groups.
“Schlesinger et al. (2018) argue that the lack of context about the world does not redeem the chatbot from the necessity of being respectful with all the social groups.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Schlesinger et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.3. MannersParticipants who received frequent follow-up questions from the task management chatbot about their pending tasks perceived the chatbot as invasive.
“Participants who received frequent follow-up questions from the task management chatbot about their pending tasks perceived the chatbot as invasive.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Toxtli et al. (2018)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.4. Moral agencyWhen the chatbot is positioned in a minority identity group, it exposes the image of that group to judgment and flaming, which is frequent in chatbot interactions.
“When the chatbot is positioned in a minority identity group, it exposes the image of that group to judgment and flaming, which is frequent in chatbot interactions (Marino, 2014).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Marino, 2014
Not checked in the free run.
Probably not a substantial claim: may not pass S1 (asserted), S3 (load-bearing), S4 (based). The quote only partly states this claim.
Premisenone given§ 3.2.2. ThoroughnessProviding thoroughness has the benefit of increasing human-likeness.
“[B1] to increase human-likeness”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.2.4. Moral agencySex talks with the male chatbot were rarely coercive or violent; his sexual preference was often questioned, and he was frequently propositioned by reported male users.
“De Angeli and Brahnam (2006) show that sex talks with the male chatbot were rarely coercive or violent; his sexual preference was often questioned, though, and he was frequently propositioned by reported male users.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli and Brahnam (2006)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.2. ThoroughnessThe repetition of vocabulary led the users to imitate it.
“the repetition of this vocabulary led the users to imitate it”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jenkins et al., 2007
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.2. ThoroughnessThis approach produces high quality utterances; on the other hand, it reduces flexibility, since the chatbot is not able to adapt the tone of the conversation based on individual users and conversational context.
“On the one hand, this approach produces high quality utterances; on the other hand, it reduces flexibility, since the chatbot is not able to adapt the tone of the conversation based on individual users and conversational context.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mairesse & Walker, 2009
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceAffective utterances improve the interpersonal relationship with a tutor chatbot.
“Ayedoun et al. (2017), Kumar et al. (2010), and Dohsaka et al. (2014) suggest that affective utterances improve the interpersonal relationship with a tutor chatbot.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Ayedoun et al. (2017)
Not checked in the free run.
- cites Kumar et al. (2010)
Not checked in the free run.
- cites Dohsaka et al. (2014)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceAn emotionally intelligent chatbot can recognize and influence users' feelings and demonstrate respect, empathy, and understanding, improving the human-chatbot relationship.
“An emotionally intelligent chatbot can recognize and influence users' feelings and demonstrate respect, empathy, and understanding, improving the humanchatbot relationship (Li et al., 2017; Salovey & Mayer, 1990).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Li et al., 2017
Not checked in the free run.
- cites Salovey & Mayer, 1990
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceThe WoZ condition was more engaging, resulting in conversations that lasted longer, with a higher number of turns.
“Quantitative results showed that the WoZ condition was more engaging, since it resulted in conversations that lasted longer, with a higher number of turns.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Portela and Granell-Canut (2017)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceAffective backchannel combined with communicative strategies significantly increased learners' confidence and desire to communicate, while reducing anxiety.
“The authors statistically demonstrated that affective backchannel, combined with communicative strategies (see Section 3.1.2) significantly increased learners' confidence and desire to communicate, while reducing anxiety.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ayedoun et al. (2017)
Not checked in the free run.
May combine two claims.
Interpretationreasoning§ 3.2.4. Moral agencyBuilding unbiased training datasets and learning algorithms that connect outputs with individual, real-world experiences are challenges to overcome.
“Building unbiased training datasets and learning algorithms that connect the outputs with individual, real-world experiences, therefore, are challenges to overcome.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ 3.2.5. Emotional IntelligenceIdentity does not matter if the challenge of regulating emotions is overcome.
“The wizards were blind to whether users thought they were talking to a chatbot or a person, which reveals that identity does not matter if the challenge of regulating emotions is overcome.”
Quote in the paperNot a substantial claimMay combine two claims.
Interpretationcitation§ 3.2.4. Moral agencyMoral agency relies on data that is biased in its nature, producing unsatisfactory results from an ethical perspective.
“Hence, moral agency relies on data that is biased in its nature, producing unsatisfactory results from an ethical perspective.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceLonger conversations (10+ turns) are needed to fulfill the needs of affection and belonging.
“Shum et al. (2018) argue that longer conversations (10+ turns) are needed to fulfill the needs of affection and belonging.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceChatbot's empathic utterances may be seen as pre-programmed and inauthentic.
“Ho et al. (2018) state that chatbot's empathic utterances may be seen as pre-programmed and inauthentic.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ho et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceAdapting chatbots' language to their current emotional state, along with personality and social role awareness, results in more believable interactions.
“(Morris, 2002) argue that adapting chatbots' language to their current emotional state, along with their personality and social role awareness, results in more believable interactions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Morris, 2002
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceChatbots do not have genuine emotions.
“Although chatbots do not have genuine emotions (Wallis & Norling, 2005), there are considerable discussions about the role of manifesting emotional cues in chatbots (Ho et al., 2018; Shum et al., 2018; Wallis & Norling, 2005).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis & Norling, 2005
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceIn Thies et al. (2017), the energetic chatbot was reported as having an enthusiasm too high to match.
“In Thies et al. (2017), the energetic chatbot was reported as having an enthusiasm too high to match.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al. (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceFive participants highlighted that the chatbot demonstrated attention to their users' feelings.
“Five participants highlighted that the chatbot demonstrated attention to their users' feelings.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites K. K. Fitzpatrick et al. (2017)
Not checked in the free run.
May combine two claims.
Interpretationcitation§ 3.2.5. Emotional IntelligenceEmpathic utterances encouraged users to engage and utter non-answer statements.
“This result shows that empathic utterances encouraged the users to engage and utter non-answers statements.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceWhen a chatbot's emotional reaction triggers a social response from the user, the chatbot has achieved group membership and users' sympathy.
“According to Wallis and Norling (2005), when a chatbot's emotional reaction triggers a social response from the user, the chatbot has achieved group membership and users' sympathy.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Wallis and Norling (2005)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.4. Moral agencyIn Shum et al. (2018), authors propose a framework for developing social chatbots and highlight that the core chat module should follow ethical design to generate unbiased, non-discriminative responses, but do not discuss specific strategies.
“In Shum et al. (2018), the authors propose a framework for developing social chatbots. The authors highlight that the core chat module should follow ethical design to generate unbiased, non-discriminative responses, but they do not discuss specific strategies for that.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligencePartners' identity (chatbot vs. person) had no effect in perceived relational and emotional experience.
“Although their results revealed that the partners' identity (chatbot vs. person) had no effect in the perceived relational and emotional experience, the chatbot condition was a WoZ setup.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ho et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable).
Interpretationreasoning§ 3.2.4. Moral agencyResearch on perceived moral agency is still necessary to develop chatbots whose social behavior is inclusive and respectful.
“As discussed in this section, research on perceived moral agency is still necessary in order to develop chatbots whose social behavior is inclusive and respectful.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceAffective moves significantly improve the perception of amicability, and marginally increased social belonging.
“Qualitative results show that affective moves significantly improve the perception of amicability, and marginally increased social belonging.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kumar et al. (2010)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceConversational logs revealed that the human tutor performed a significantly higher number of affective moves in that context.
“Conversational logs revealed that the human tutor performed a significantly higher number of affective moves in that context.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Kumar et al. (2010)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Personalizing the amount of personal information a chatbot can access and store is required to establish a relation of trust and reciprocity in workplace environments.
“Duijvelshoff (2017) state that personalizing the amount of personal information a chatbot can access and store is required to establish a relation of trust and reciprocity in workplace environments.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijvelshoff (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Chatbots whose focus is engagement need to personalize generation of responses for different users' backgrounds, personal interests, and needs to serve their needs for communication, affection, and social belonging.
“Shum et al. (2018) argue that chatbots whose focus is engagement need to personalize the generation of responses for different users' backgrounds, personal interests, and needs in order to serve their needs for communication, affection, and social belonging.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.5. Emotional IntelligenceReciprocity and self-disclosure are strong predictors of rapport and user satisfaction.
“Results demonstrated that reciprocity and self-disclosure are strong predictors of rapport and user satisfaction.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites S. Lee and Choi (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceA chatbot needs to combine usefulness with emotion by asking questions that help clarify users' intentions.
“Shum et al. (2018) argue that a chatbot needs to combine usefulness with emotion by asking questions that help to clarify the users' intentions.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Duijst (2017) found no significant effect of personalization on user experience with the financial assistant chatbot.
“Although Duijst (2017) has found no significant effect of personalization on the user experience with the financial assistant chatbot, the study applies personalization as the ability to provide empathic responses according to the users' issues, where emotional intelligence plays a role.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.5. Emotional IntelligenceKeeping track of the conversation was reported as an empathic behavior and resulted in mutual affection.
“Keeping track of the conversation was reported as an empathic behavior and resulted in mutual affection.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Portela and GranellCanut (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Use of the task-assignment chatbot varied depending on participants' levels of hierarchy.
“When exploring how teammates used a task-assignment chatbot, Toxtli et al. (2018) found that the use of the chatbot varied depending on the participants' levels of hierarchy.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Toxtli et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Two participants expected chatbots to retain context from previous interactions to improve recommendations.
“In Jain, Kumar, et al. (2018), two participants also expected chatbots to retain context from previous interactions to improve recommendations.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).
Interpretationnone given§ 3.2.5. Emotional IntelligenceUsing emotional utterances in a personalized, context relevant way is still a challenge.
“Using emotional utterances in a personalized, context relevant way is still a challenge.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Eight participants reported dissatisfaction with the chatbot's generic guidance to specific places.
“In the ethnography data collection study (Tallyn et al., 2018), eight participants reported dissatisfaction with the chatbot's generic guidance to specific places.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Tallyn et al., 2018
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation§ 3.2.5. Emotional IntelligenceAdopting the strategy of combining usefulness with emotion requires the chatbot to handle message understanding, emotion and sentiment tracking, session context modeling, and user profiling.
“Adopting this strategy requires the chatbot to handle message understanding, emotion and sentiment tracking, session context modeling, and user profiling Shum et al. (2018).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Shum et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:In HCI, personalization is used to customize the interface toward user familiarity.
“in HCI, personalization is used to customize the interface toward user familiarity (Fan & Poole, 2006).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Fan & Poole, 2006
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:One participant suggested that choice of text color and font size should be customizable.
“In Jenkins et al. (2007), one participant suggested that the choice of text color and font size should be customizable.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jenkins et al. (2007)
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable).
Interpretationcitation§ actions:There is a need to personalize interaction to individual user's mental models.
“This outcome support to the need to personalize the interaction to individual user's mental models.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ actions:Duijst (2017) observed that participants faced difficulties with small letters, and concluded that adapting interface to provide accessibility needs to be considered.
“Duijst (2017) also observed that participants faced difficulties with small letters, and concluded that adapting the interface to provide accessibility also needs to be considered.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijst (2017)
Not checked in the free run.
May combine two claims.
Premisecitation§ actions:Users with low social-agent orientation emphasize the utilitarian value of the system, while users with high social-agent orientation see the system as a humanized assistant.
“V. Q. Liao et al. (2016) also found that users with low social-agent orientation emphasize the utilitarian value of the system, while users with high social-agent orientation see the system as a humanized assistant.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites V. Q. Liao et al. (2016)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ actions:Interpersonal relationship can be enriched by adapting chatbots' language to match user's context, energy, and formality.
“Interpersonal relationship can also be enriched by adapting the chatbots' language to match the user's context, energy, and formality; the ability to appropriately use language is discussed in Section 3.2.2.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.2.6. PersonalizationPersonalization can improve rapport and cooperation, ultimately increasing engagement with chatbots.
“Grounded in robots and artificial agents' literature, V. Q. Liao et al. (2016) argue that personalization can improve rapport and cooperation, ultimately increasing engagement with chatbots.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites V. Q. Liao et al. (2016)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.2.6. PersonalizationIn task-oriented contexts, personalization aims to increase relevance of services to particular users.
“In task-oriented contexts, such as task management, personalization aims to increase the relevance of services to particular users (V. Q. Liao et al., 2016).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites V. Q. Liao et al., 2016
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ actions:To enrich efficiency and productivity of interaction, a chatbot needs to have memory of previous interactions as well as learn user's preferences and disclosed personal information.
“To enrich the efficiency and productivity of the interaction, a chatbot needs to have memory of previous interactions as well as learn user's preferences and disclosed personal information (Thies et al., 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al., 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Participants in Zamora (2017) reported that personal data and social media content may be inappropriate topics for chatbots because they can be sensitive.
“Similarly, participants in Zamora (2017) reported that personal data and social media content may be inappropriate topics for chatbots because they can be sensitive.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Zamora (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ 3.2.5. Emotional IntelligenceAdaptation to dynamic context improves the sense of personalized interactions.
“Adaption to the dynamic context also improves the sense of personalized interactions, which is discussed in the next section.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Interviews with 12 participants generated 59 statements about how learning from experience promotes chatbots' authenticity.
“In Neururer et al. (2018), interviews with 12 participants generated a total of 59 statements about how learning from experience promotes chatbots' authenticity.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Neururer et al. (2018)
Not checked in the free run.
The quote only partly states this claim.
Interpretationcitation§ 3.3.1. IdentityAttributing identity to a chatbot increases engagement.
“[B1] to increase engagement: when evaluating signals of playful interactions, Q. V. Liao et al. (2018) found that agent-oriented conversations (asking about an agent's traits and status) are consistent with the tendency to anthropomorphize the agent and engage in chit-chat.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Q. V. Liao et al. (2018)
Not checked in the free run.
- cites Silvervarg and Jönsson (2013)
Not checked in the free run.
- cites Araujo (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3. PersonificationIn HCI, researchers argue that using a personified character in the user interface is a natural way to support interaction.
“In the HCI field, researchers argue that using a personified character in the user interface is a natural way to support the interaction (Koda, 2003).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Koda, 2003
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.
Interpretationcitation§ actions:If user prefers a more generic chatbot, then it would not store personal data, potentially increasing engagement with more resistant users.
“If the user prefers a more generic chatbot, then it would not store personal data, potentially increasing the engagement with more resistant users.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S1 (asserted), S3 (load-bearing).
Premisecitation§ actions:Users should be able to choose level of chatbot's attributes, for example, agent's look and persona.
“V. Q. Liao et al. (2016) suggest that users should be able to choose the level of the chatbot's attributes, for example, the agent's look and persona.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites V. Q. Liao et al. (2016)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ actions:Thies et al. (2017) raise possibility of offering an 'incognito' mode for chatbots or asking chatbot to forget what was said in previous utterances.
“Thies et al. (2017) raise the possibility of offering an 'incognito' mode for chatbots or asking the chatbot to forget what was said in previous utterances.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al. (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationreasoning§ actions:This differentiation could be first signal to personalize further conversation, such as focusing on more productive or playful interactions.
“This differentiation could be the first signal to personalize further conversation, such as focusing on more productive or playful interactions.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Privacy concerns may be reduced if a chatbot demonstrates care about privacy.
“These concerns may be reduced if a chatbot demonstrates care about privacy (Duijvelshoff, 2017).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijvelshoff, 2017
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3. PersonificationTalking to a machine affords it a new identity.
“According to De Angeli (2005), talking to a machine affords it a new identity .”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli (2005)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.3.1. IdentityChatbots lack agency to choose what social group to which they want to belong, but designers attribute identity to them, intentionally or not, when they define the way a chatbot talks or behaves.
“Although chatbots lack the agency to choose what social group to which they want to belong, designers attribute identity to them, intentionally or not, when they define the way a chatbot talks or behaves (Cassell, 2009).”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Cassell, 2009
Not checked in the free run.
May combine two claims.
Premisecitation§ actions:Conversation logs showed that tailored questions prompted users to report more detail about their experience, which is important in ethnography research.
“As discussed in Section 3.1.2, quick replies may be seen as restrictive from an interactional perspective; however, conversation logs showed that the tailored questions prompted the users to report more detail about their experience, which is important in ethnography research.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Tallyn et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Chatbots should present strategies to learn from cultural, behavioral, personal, conversational, and contextual interaction data.
“Neururer et al. (2018) state that chatbots should present strategies to learn from cultural, behavioral, personal, conversational, and contextual interaction data.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Neururer et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).
Interpretationcitation§ actions:Users with low social-agent orientation could use a non-humanized interface, which would better represent their initial perspective.
“By doing so, users with low social-agent orientation could use a non-humanized interface, which would better represent their initial perspective.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ actions:Interviews with potential users revealed that users should be able to manage what information chatbot knows about them and decide whether chatbot can learn from previous interactions.
“Regarding chatbots' learning capabilities, in Duijvelshoff (2017), interviews with potential users revealed that users should be able to manage what information the chatbot knows about them and decide whether the chatbot can learn from previous interactions or not.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Duijvelshoff (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3. PersonificationChatbot embodiment can be created through narrative without any visual help.
“Although research on personification is more common in the Embodied Conversational Agents field, De Angeli, Johnson, and Coventry (2001) claim that chatbot embodiment can be created through narrative without any visual help.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites De Angeli, Johnson, and Coventry (2001)
Not checked in the free run.
Classified as probably not a substantial claim.
Interpretationcitation§ 3.3.1. IdentityAttributing identity to a chatbot requires balancing the identity and the technical capabilities.
“[C2] to balance the identity and the technical capabilities: the literature comparing embodied vs. disembodied conversational agents yields contradictory results regarding the relevance of a human representation.”
Quote in the paperSubstantial claim0 of 3 sources checked- cites Corti and Gillespie (2016)
Not checked in the free run.
- cites Ciechanowski et al. (2018)
Not checked in the free run.
- cites Gnewuch et al. (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ actions:Chatbot should remember user's preferences disclosed in previous conversations.
“Thies et al. (2017) also suggest that the chatbot should remember user's preferences disclosed in previous conversations.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Thies et al. (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3.1. IdentityCandello et al. (2017) found that users perceive machine-like typefaces as more chatbot-like.
“When evaluating different typefaces for a financial adviser chatbot, Candello et al. (2017) found that users perceive machine-like typefaces as more chatbot-like, although they did not find strong evidence of handwriting-like typefaces conveying humanness.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Candello et al. (2017)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation§ 3.3.2. PersonalityAttributing personality to a chatbot requires adapting humor to the users' culture.
“[C1] to adapt humor to the users' culture: sense of humor is highly shaped by cultural environment (Ruch, 1998).”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Ruch (1998)
Not checked in the free run.
- cites Ptaszynski et al. (2010)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.3.1. IdentityBrahnam and De Angeli (2012) showed that people spoke more often about physical appearance and used more swear and sexual words with the female-presenting chatbot.
“When evaluating the effect of gender identity on disinhibition, Brahnam and De Angeli (2012) showed that people spoke more often about physical appearance and used more swear and sexual words with the female-presenting chatbot, and racist attacks were observed in interactions with black-representing chatbots.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Brahnam and De Angeli (2012)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Study design and conductreasoning§ 6. LimitationsSince the definition of chatbot is not consolidated in the literature and chatbots have been studied across several different domains, some studies that include social aspects of chatbots may not have been found.
“Secondly, since the definition of chatbot is not consolidated in the literature and chatbots have been studied across several different domains, some studies that include social aspects of chatbots may not have been found.”
Quote in the paperNot a substantial claimClassified as probably not a substantial claim. May combine two claims.
Study design and conductreasoning§ 6. LimitationsWe adopted several synonyms in our research string and used Google Scholar as search engine.
“To account for that, we adopted several synonyms in our research string and used Google Scholar as search engine, which provides a fairly comprehensive indexing of the literature in more domains.”
Quote in the paperSubstantial claimMay combine two claims.
Study design and conductreasoning§ 6. LimitationsBoth the conceptual framework and the relationships amongst the characteristics were derived based on outcomes the surveyed studies explicitly reported.
“and both the conceptual framework and the relationships amongst the characteristics were derived based on outcomes the surveyed studies explicitly reported.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.3.2. PersonalityOutcomes consistently suggest that students prefer a chatbot that is not overly polite, but has some attitude.
“Outcomes consistently suggest that students prefer a chatbot that is not overly polite, but has some attitude.”
Quote in the paperNot a substantial claim0 of 3 sources checked- cites Ayedoun et al., 2017
Not checked in the free run.
- cites Kumar et al., 2010
Not checked in the free run.
- cites Sjödén et al., 2011
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductreasoning§ 6. LimitationsSince this survey focused on disembodied, text-based chatbots, the literature on embodied and speech-based conversational agents was excluded.
“Firstly, since this survey focused on disembodied, text-based chatbots, the literature on embodied and speech-based conversational agents was excluded.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationcitation§ 7. ConclusionConscientiousness, thoroughness, and proactivity might be covered by the cooperative principle.
“For example, conscientiousness , thoroughness , and proactivity might be covered by the cooperative principle (Grice et al., 1975)”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Grice et al., 1975
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductown data§ 6. LimitationsThe conceptual model of social characteristics was derived through a coding process inspired by qualitative methods, such as Grounded Theory.
“Finally, the conceptual model of social characteristics was derived through a coding process inspired by qualitative methods, such as Grounded Theory.”
Quote in the paperSubstantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Study design and conductreasoning§ 6. LimitationsLike any qualitative coding methods, it relies on the researchers' subjective assessment.
“Like any qualitative coding methods, it relies on the researchers' subjective assessment.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.
Premisecitation§ 3.3.2. PersonalityPuns are restricted to a specific culture and language, with low portability.
“However, puns are restricted to a specific culture and language, with low portability.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ptaszynski et al. (2010)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3.2. PersonalityJain, Kumar, et al. (2018) discussed that a chatbot's personality should match its domain.
“Jain, Kumar, et al. (2018) discussed that a chatbot's personality should match its domain.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Jain, Kumar, et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationnone given§ 4.1. A note on chatbots' humannessThe social characteristics identified in the survey align well with characteristics that are present in human-human interactions.
“The social characteristics identified in the survey align well with characteristics that are present in human-human interactions.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ 6. LimitationsThis decision may have caused the under-representation of certain research domains.
“Additionally, this decision may have caused the under-representation of certain research domains.”
Quote in the paperNot a substantial claimMay combine two claims.
Premisecitation§ 3.3.1. IdentityCiechanowski et al. (2018) show that simpler text-based chatbots with no visual, human identity resulted in less of an uncanny effect and reduced negative affect.
“in contrast, when evaluating a website assistant chatbot, Ciechanowski et al. (2018) show that simpler text-based chatbots with no visual, human identity resulted in less of an uncanny effect and reduced negative affect.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ciechanowski et al. (2018)
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3.2. PersonalityA consistent personality helps the chatbot to gain the users' confidence and trust.
“In Shum et al. (2018) and (Sj¨ od´ en et al., 2011), the authors argue that a consistent personality helps the chatbot to gain the users' confidence and trust.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Shum et al. (2018)
Not checked in the free run.
- cites Sjödén et al. (2011)
Not checked in the free run.
May combine two claims.
Premisecitation§ 3.3.2. PersonalityIn Ptaszynski et al. (2010), the joker chatbot was perceived as more human-like, knowledgeable, and funny, and participants felt more engaged.
“In Ptaszynski et al. (2010), the joker chatbot was perceived as more human-like, knowledgeable, and funny, and participants felt more engaged.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Ptaszynski et al. (2010)
Not checked in the free run.
May combine two claims.
Interpretationcitation§ 4.1. A note on chatbots' humannessThis survey shows the benefits of considering these characteristics when developing chatbots, which is supported by the Media Equation theory.
“On the one hand, this survey shows the benefits of considering these characteristics when developing chatbots, which is supported by the Media Equation theory (Nass & Moon, 2000; Nass et al., 1993); we identified the domains in which each characteristic was studied.”
Quote in the paperNot a substantial claim0 of 2 sources checked- cites Nass & Moon, 2000
Not checked in the free run.
- cites Nass et al., 1993
Not checked in the free run.
Probably not a substantial claim: may not pass S3 (load-bearing).
Interpretationreasoning§ 4.1. A note on chatbots' humannessAs chatbots enrich their communication and social skills, their perceived social role may approach human profiles.
“Still, as the chatbots enrich their communication and social skills, their perceived social role may approach human profiles.”
Quote in the paperNot a substantial claimProbably not a substantial claim: may not pass S3 (load-bearing).
Premisecitation§ 3.3.2. PersonalityMairesse and Walker (2009) observed that some utterances sounded unnatural because a human's personality is a continuous phenomenon, rather than a discrete one.
“In Mairesse and Walker (2009), the researchers intentionally generated utterances to reflect extreme personalities; as a result, they observed that some utterances sounded unnatural because a human's personality is a continuous phenomenon, rather than a discrete one.”
Quote in the paperNot a substantial claim0 of 1 sources checked- cites Mairesse and Walker (2009)
Not checked in the free run.
Classified as probably not a substantial claim.
Study design and conductreasoning§ 6. LimitationsTo mitigate this threat, the researchers discussed the social characteristics and categories during in-person meetings until reaching consensus.
“To mitigate this threat, the researchers discussed the social characteristics and categories during in-person meetings until reaching consensus, and both the conceptual framework and the relationships amongst the characteristics were derived based on outcomes the surveyed studies explicitly reported.”
Quote in the paperSubstantial claim
The paper relies on this without support.
The increasing need to approximate conversational interaction styles raises users' expectations that chatbots present social behaviors habitual in human-human communication.
“The increasing need to approximate conversational interaction styles raises expectations for chatbots to present social behaviors that are habitual in human-human communication.”
The paper relies on this without support.
Chatbots' social characteristics knowledge is spread across several domains in which chatbots have been studied.
“Although chatbots' social characteristics have been explored in the literature, this knowledge is spread across several domains in which chatbots have been studied, such as customer services, education, finances, and travel.”
The paper relies on this without support.
A lack of studies brings together the social characteristics that influence the way users perceive and behave toward chatbots.
“Whilst the literature has extensively reviewed the technical aspects of chatbots design (e.g., Ahmad, Che, Zainal, Rauf, and Adnan (2018); Deshpande, Shahane, Gadre, Deshpande, and Joshi (2017); Masche and Le (2017); Ramesh, Ravishankaran, Joshi, and Chandrasekaran (2017); Thorne (2017); Walgama and Hettige (2017); Winkler and S¨ ollner (2018)), a lack of studies brings together the social char”
The paper relies on this without support.
The literature presents no coherent definition of chatbots.
“The literature presents no coherent definition of chatbots; thus, to find relevant studies we used a search string that includes the synonyms 'chatbots, chatterbots, conversational agents, conversational interfaces, conversational systems, conversation systems, dialogue systems, digital assistants, intelligent assistants, conversational user interfaces, and conversational UI' .”
The paper relies on this without support.
Most studies do not explicitly label their results as social characteristics/traits.
“We decided to not include terms that relate to social characteristics/traits, because most studies do not explicitly label their results as such.”
The paper relies on this without support.
The characteristics and categories are seldom explicitly highlighted in the literature.
“Noticeably, the characteristics and categories are seldom explicitly highlighted to in the literature, so the conceptual model was derived using a qualitative coding process inspired by methods such as Grounded Theory (Auerbach & Silverstein, 2003) (open coding stage).”
The paper relies on this without support.
The set of social characteristics identified from the surveyed literature is the relevant set for designing chatbot social behavior.
“In this survey, we investigated the literature on disembodied, text-based chatbots to answer the question 'What chatbot social characteristics benefit human interactions and what are the challenges and strategies associated with them?'”
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
E-learning and mental health represent relevant interaction contexts, which have also seen great prominence in recent publications.
“E-learning and mental health represent relevant interaction contexts, which have also seen great prominence in recent publications (Androutsopoulos et al., 1995; Chaves & Gerosa, 2021; Følstad & Skjuve, 2019; Hauswald et al., 2016).”
From Charting the Evolution and Future of Conversational Agents: A Research Agenda Along Five Waves and New Frontiers (2024) · cites this paper as Chaves & Gerosa, 2021
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
General-purpose study percentage is understated
MinorThe paper identifies 19 general-purpose chatbot studies out of 56 surveyed studies. That is approximately 34%, not the reported 33%.
Reported 33 · recomputed 33.928571
“General purpose chatbots reflect 33% of the surveyed studies. Most general purpose chatbots (16 out of 19) are designed to handle topic-unrestricted conversations.”
Real-chatbot study subgroups total 36, not 35
MinorThe three groups described among the studies using real chatbots contain 18, 9, and 9 studies, totaling 36 rather than the reported 35.
Reported 35 · recomputed 36
“Most surveyed studies adopted real chatbots (35 out of 56); among them, 18 studies analyze logs of conversations or users' perceptions of third-party chatbots such as Cleverbot (e.g., Corti and Gillespie (2016)), Talkbot (e.g., Brahnam and De Angeli (2012)), and Woebot K. K. Fitzpatrick et al. (2017). Nine studies introduce a selfdeveloped architecture and/or dialogue management”
Cites
Grice, H. P. (1975) · Speech Acts · doi:10.1163/9789004368811_003 · Cited by 23,221 · see citing works
Salovey, P., & Mayer, J. D. (1990) · Imagination, Cognition and Personality · doi:10.2190/dugg-p24e-52wk-6cdg · Cited by 10,484 · see citing works
I.—COMPUTING MACHINERY AND INTELLIGENCE
TURING, A. M. (1950) · Mind · doi:10.1093/mind/lix.236.433 · Cited by 10,290 · cited 2× · see citing works
“The origin of the chatbots concept dates back to 1950 [Turing 1950].”
BackgroundThe emerging field of emotion regulation: an integrative review
Gross, J. J. (1998) · Review of General Psychology · doi:10.1037/1089-2680.2.3.271 · Cited by 9,916 · see citing works
An alternative "description of personality": The Big-Five factor structure.
Goldberg, L. R. (1990) · Journal of Personality and Social Psychology · doi:10.1037//0022-3514.59.6.1216 · Cited by 6,652 · see citing works
Validation of the five-factor model of personality across instruments and observers.
McCrae, R. R., & Costa, P. T. (1987) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.52.1.81 · Cited by 6,404 · see citing works
Computer-Mediated Communication: Impersonal, Interpersonal, and Hyperpersonal Interaction
WALTHER, J. B. (1996) · Communication Research · doi:10.1177/009365096023001001 · Cited by 4,798 · cited 1× · see citing works
“CMC is by itself more impersonal than face-to-face conversations [Walther 1992, 1996]; even so, current online communication media has been successfully used to initiate, develop, and maintain interpersonal relationships [Walther 2011].”
BackgroundIdentity Theory and Social Identity Theory
Stets, J. E., & Burke, P. J. (2000) · Social Psychology Quarterly · doi:10.2307/2695870 · Cited by 4,464 · see citing works
ELIZA—a computer program for the study of natural language communication between man and machine
Weizenbaum, J. (1966) · Communications of the ACM · doi:10.1145/365153.365168 · Cited by 4,452 · see citing works
Personality trait structure as a human universal.
McCrae, R. R., & Costa, P. T. (1997) · American Psychologist · doi:10.1037/0003-066x.52.5.509 · Cited by 4,234 · see citing works
Machines and Mindlessness: Social Responses to Computers
Nass, C., & Moon, Y. (2000) · Journal of Social Issues · doi:10.1111/0022-4537.00153 · Cited by 4,022 · see citing works
Fitzpatrick, K. K., Darcy, A., & Vierhile, M. (2017) · JMIR Mental Health · doi:10.2196/mental.7785 · Cited by 2,730 · see citing works
Interpersonal Effects in Computer-Mediated Interaction
Walther, J. B. (1992) · Communication Research · doi:10.1177/009365092019001003 · Cited by 2,535 · see citing works
Gray, H. M., Gray, K., & Wegner, D. M. (2007) · Science · doi:10.1126/science.1134475 · Cited by 2,342 · see citing works
Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016) · Communications of the ACM · doi:10.1145/2818717 · Cited by 1,973 · see citing works
Zuckerman, M., Kuhlman, D. M., Joireman, J. A., Teta, P., & Kraft, M. (1993) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.65.4.757 · Cited by 1,390 · see citing works
Conversational agents in healthcare: a systematic review
Laranjo, L., Dunn, A. G., Tong, H. L., Kocaballi, A. B., Chen, J., Bashir, R., Surian, D., Gallego, B., Magrabi, F., Lau, A. Y. S., et al. (2018) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocy072 · Cited by 1,388 · cited 2× · see citing works
“elements (such as quick replies) compared to typing the responses, Lasek and Jessa (2013) observed that users that start the interaction by clicking an option are more likely to continue the conversation if the next exchange also has visual elements as optional affordances.”
ResultWatts, R. J. (2003) · Cambridge University Press eBooks · doi:10.1017/cbo9780511615184 · Cited by 1,214 · see citing works
Personalizing Dialogue Agents: I have a dog, do you have pets too?
Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., & Weston, J. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1205 · Cited by 1,177 · see citing works
Luger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176 · see citing works
Araujo, T. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.03.051 · Cited by 1,156 · see citing works
Walther, J. B. (2007) · Computers in Human Behavior · doi:10.1016/j.chb.2006.05.002 · Cited by 915 · see citing works
Hill, J., Randolph Ford, W., & Farreras, I. G. (2015) · Computers in Human Behavior · doi:10.1016/j.chb.2015.02.026 · Cited by 856 · see citing works
Brandtzaeg, P. B., & Følstad, A. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70284-1_30 · Cited by 788 · see citing works
From Eliza to XiaoIce: Challenges and opportunities with social chatbots
Shum, H.-Y., He, X.-D., & Li, D. (2018) · Frontiers of Information Technology & Electronic Engineering · doi:10.1631/fitee.1700826 · Cited by 749 · cited 30× · see citing works
“According to [Shum et al. 2018], leveraging the context can also help to smoothly guide the user to a target topic.”
BackgroundMethodInfluentialWizard of Oz studies — why and how
Dahlbäck, N., Jönsson, A., & Ahrenberg, L. (1993) · Knowledge-Based Systems · doi:10.1016/0950-7051(93)90017-n · Cited by 706 · see citing works
In the shades of the uncanny valley: An experimental study of human–chatbot interaction
Ciechanowski, L., Przegalińska, A., Magnuski, M., & Gloor, P. A. (2018) · Future Generation Computer Systems · doi:10.1016/j.future.2018.01.055 · Cited by 680 · see citing works
Ho, A., Hancock, J., & Miner, A. S. (2018) · Journal of Communication · doi:10.1093/joc/jqy026 · Cited by 629 · cited 10× · see citing works
“[Ho et al. 2018] measured users’ experience in conversations with a chatbot compared to a human partner as well as the amount of intimacy disclosure and cognitive reappraisal.”
BackgroundInfluentialUnleashing the Potential of Chatbots in Education: A State-Of-The-Art Analysis
Winkler, R., & Soellner, M. (2018) · Academy of Management Proceedings · doi:10.5465/ambpp.2018.15903abstract · Cited by 581 · see citing works
Nowak, K. L., & Rauh, C. (2005) · Journal of Computer-Mediated Communication · doi:10.1111/j.1083-6101.2006.tb00308.x · Cited by 557 · see citing works
Chatbots and the new world of HCI
Følstad, A., & Brandtzæg, P. B. (2017) · interactions · doi:10.1145/3085558 · Cited by 520 · see citing works
Dale, R. (2016) · Natural Language Engineering · doi:10.1017/s1351324916000243 · Cited by 488 · see citing works
Tennenhouse, D. L. (2000) · Communications of the ACM · doi:10.1145/332833.332837 · Cited by 475 · see citing works
Fan, H., & Poole, M. S. (2006) · Journal of Organizational Computing and Electronic Commerce · doi:10.1080/10919392.2006.9681199 · Cited by 404 · see citing works
Lee, S., & Choi, J. (2017) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2017.02.005 · Cited by 388 · see citing works
Evaluating and Informing the Design of Chatbots
Jain, M., Kumar, P., Kota, R., & Patel, S. N. (2018) · Proceedings of the 2018 Designing Interactive Systems Conference · doi:10.1145/3196709.3196735 · Cited by 376 · see citing works
Style transfer through back-translation
Prabhumoye, S., Tsvetkov, Y., Salakhutdinov, R., & Black, A. W. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1080 · Cited by 348 · see citing works
Gong, L. (2008) · Computers in Human Behavior · doi:10.1016/j.chb.2007.05.007 · Cited by 338 · see citing works
The media inequality: Comparing the initial human-human and human-AI social interactions
Mou, Y., & Xu, K. (2017) · Computers in Human Behavior · doi:10.1016/j.chb.2017.02.067 · Cited by 337 · see citing works
Wallace, R. S. (2007) · Springer eBooks · doi:10.1007/978-1-4020-6710-5_13 · Cited by 335 · see citing works
(2003) · doi:10.5040/9798216187646 · Cited by 331 · see citing works
A survey of software learnability: metrics, methodologies and guidelines
Grossman, T., Fitzmaurice, G., & Attar, R. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518803 · Cited by 322 · see citing works
Chatbots: changing user needs and motivations
Brandtzaeg, P. B., & Følstad, A. (2018) · Interactions · doi:10.1145/3236669 · Cited by 322 · see citing works
Survey of conversational agents in health
Montenegro, J. L. Z., da Costa, C. A., & da Rosa Righi, R. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.03.054 · Cited by 322 · see citing works
Social intelligence − empathy = aggression?
Björkqvist, K., Österman, K., & Kaukiainen, A. (2000) · Aggression and Violent Behavior · doi:10.1016/s1359-1789(98)00029-9 · Cited by 316 · see citing works
Theoretical Importance of Contingency in Human-Computer Interaction
Sundar, S. S., Bellur, S. S., Oh, J., Jia, H., & Kim, H. S. (2014) · Communication Research · doi:10.1177/0093650214534962 · Cited by 304 · see citing works
Himma, K. E. (2009) · Ethics and Information Technology · doi:10.1007/s10676-008-9167-5 · Cited by 276 · see citing works
Allen, C., Wallach, W., & Smit, I. (2006) · IEEE Intelligent Systems · doi:10.1109/mis.2006.83 · Cited by 239 · see citing works
Methods and tools: a method for evaluating the communicability of user interfaces
Prates, R. O., de Souza, C. S., & Barbosa, S. D. J. (2000) · interactions · doi:10.1145/328595.328608 · Cited by 220 · see citing works
The uncanny of mind in a machine: Humanoid robots as tools, agents, and experiencers
Appel, M., Izydorczyk, D., Weber, S., Mara, M., & Lischetzke, T. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2019.07.031 · Cited by 211 · see citing works
A Survey of Design Techniques for Conversational Agents
Ramesh, K., Ravishankaran, S., Joshi, A., & Chandrasekaran, K. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6544-6_31 · Cited by 170 · see citing works
I'm Sorry, Dave, I'm Afraid I Can't Do That: Chatbot Perception and Expectations
Zamora, J. (2017) · Proceedings of the 5th International Conference on Human Agent Interaction · doi:10.1145/3125739.3125766 · Cited by 164 · see citing works
Anthropomorphism, agency, and ethopoeia: computers as social actors
Nass, C., Steuer, J., Tauber, E., & Reeder, H. (1993) · INTERACT '93 and CHI '93 conference companion on Human factors in computing systems - CHI '93 · doi:10.1145/259964.260137 · Cited by 162 · see citing works
Why Developers Are Slacking Off: Understanding How Software Teams Use Slack
Lin, B., Zagalsky, A., Storey, M., & Serebrenik, A. (2016) · ACM Conference on Computer Supported Cooperative Work (CSCW) · doi:10.1145/2818052.2869117 · Cited by 161 · see citing works
You always hurt the one you love: Strategies and tactics in interpersonal conflict
Fitzpatrick, M. A., & Winke, J. (1979) · Communication Quarterly · doi:10.1080/01463377909369319 · Cited by 153 · see citing works
Gender affordances of conversational agents
Brahnam, S., & Angeli, A. D. (2012) · Interacting with Computers · doi:10.1016/j.intcom.2012.05.001 · Cited by 149 · see citing works
Banks, J. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.08.028 · Cited by 145 · see citing works
Schlesinger, A., O'Hara, K. P., & Taylor, A. S. (2018) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173889 · Cited by 142 · see citing works
Media inequality in conversation
Shechtman, N., & Horowitz, L. M. (2003) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/642611.642661 · Cited by 139 · see citing works
Challenges in Chatbot Development
Abdellatif, A., Costa, D. E., Badran, K., Abdalkareem, R., & Shihab, E. (2020) · International Conference on Mining Software Repositories (MSR) · doi:10.1145/3379597.3387472 · Cited by 129 · see citing works
Ayedoun, E., Hayashi, Y., & Seta, K. (2019) · International Journal of Artificial Intelligence in Education · doi:10.1007/s40593-018-0171-6 · Cited by 128 · see citing works
Corti, K., & Gillespie, A. (2016) · Computers in Human Behavior · doi:10.1016/j.chb.2015.12.039 · Cited by 118 · see citing works
Brown, P. (2015) · Elsevier eBooks · doi:10.1016/b978-0-08-097086-8.53072-4 · Cited by 117 · see citing works
Artificially intelligent conversational agents in libraries
Rubin, V. L., Chen, Y., & Thorimbert, L. M. (2010) · Library Hi Tech · doi:10.1108/07378831011096196 · Cited by 113 · see citing works
Review of Chatbots Design Techniques
Ahmad, N. A., Hafiz, M., Zainal, A., Fairuz, M., & Adnan, Z. (2018) · International Journal of Computer Applications · doi:10.5120/ijca2018917606 · Cited by 101 · see citing works
Keijsers, M., & Bartneck, C. (2018) · ACM/IEEE International Conference on Human-Robot Interaction (HRI) · doi:10.1145/3171221.3171266 · Cited by 100 · see citing works
Neural personalized response generation as domain adaptation
Zhang, W., Zhu, Q., Wang, Y., Zhao, Y., & Liu, T. (2018) · World Wide Web · doi:10.1007/s11280-018-0598-6 · Cited by 94 · see citing works
Liao, Q. V., Davis, M. J., Geyer, W., Muller, M., & Shami, N. S. (2016) · Designing Interactive Systems Conference · doi:10.1145/2901790.2901842 · Cited by 93 · see citing works
Computers as persuasive social actors
Fogg, B. J. (2003) · Elsevier eBooks · doi:10.1016/b978-155860643-2/50007-x · Cited by 92 · see citing works
Typefaces and the Perception of Humanness in Natural Language Chatbots
Candello, H. C. D. S. P., Pinhanez, C. S., & Figueiredo, F. (2017) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025919 · Cited by 91 · see citing works
#MeToo Alexa: How Conversational Systems Respond to Sexual Harassment
Curry, A. C., & Rieser, V. (2018) · doi:10.18653/v1/w18-0802 · Cited by 87 · see citing works
Brown, P., Levinson, S., & Gumperz, J. (2021) · Cross-Cultural Pragmatics · doi:10.1017/cbo9780511813085 · Cited by 87 · see citing works
‘Realness’ in Chatbots: Establishing Quantifiable Criteria
Morrissey, K., & Kirakowski, J. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-39330-3_10 · Cited by 82 · see citing works
Avula, S., Chadwick, G., Arguello, J., & Capra, R. (2018) · Conference on Human Information Interaction and Retrieval · doi:10.1145/3176349.3176380 · Cited by 80 · see citing works
Evaluating the language resources of chatbots for their potential in English as a second language
Coniam, D. (2008) · ReCALL · doi:10.1017/s0958344008000815 · Cited by 75 · see citing works
Perceptions on Authenticity in Chat Bots
Neururer, M., Schlögl, S., Brinkschulte, L., & Groth, A. (2018) · Multimodal Technologies and Interaction · doi:10.3390/mti2030060 · Cited by 75 · see citing works
Convey: Exploring the Use of a Context View for Chatbots
Jain, M., Kota, R., Kumar, P., & Patel, S. N. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174042 · Cited by 74 · see citing works
How interface agents affect interaction between humans and computers
Forlizzi, J., Zimmerman, J., Mancuso, V., & Kwak, S. (2007) · Proceedings of the 2007 conference on Designing pleasurable products and interfaces · doi:10.1145/1314161.1314180 · Cited by 69 · see citing works
Analysis of User Interaction with Service Oriented Chatbot Systems
Jenkins, M.-C., Churchill, R., Cox, S. J., & Smith, D. J. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-73110-8_9 · Cited by 66 · see citing works
A new friend in our smartphone?
Portela, M., & Granell, C. (2017) · International Conference on Human Computer Interaction (Interacción) · doi:10.1145/3123818.3123826 · Cited by 66 · see citing works
Tallyn, E., Fried, H., Gianni, R., Isard, A., & Speed, C. (2018) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174178 · Cited by 66 · see citing works
The Racial Formation of Chatbots
Marino, M. (2014) · CLCWeb Comparative Literature and Culture · doi:10.7771/1481-4374.2560 · Cited by 62 · see citing works
Socially Capable Conversational Tutors Can Be Effective in Collaborative Learning Situations
Kumar, R. V., Ai, H., Beuth, J., & Rosé, C. P. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13388-6_20 · Cited by 59 · see citing works
Conversational Agents and Mental Health
Miner, A. S., Chow, A., Adler, S., Zaitsev, I., Tero, P., Darcy, A. M., & Paepcke, A. (2016) · International Conference on Human-Agent Interaction (HAI) · doi:10.1145/2974804.2974820 · Cited by 56 · see citing works
WHAT MAKES ANY AGENT A MORAL AGENT? REFLECTIONS ON MACHINE CONSCIOUSNESS AND MORAL AGENCY
Parthemore, J., & Whitby, B. (2013) · International Journal of Machine Consciousness · doi:10.1142/s1793843013500017 · Cited by 53 · see citing works
Six modes of proactive resource management
Salovaara, A., & Oulasvirta, A. (2004) · Nordic Conference on Human-Computer Interaction · doi:10.1145/1028014.1028022 · Cited by 50 · see citing works
Deryugina, O. V. (2010) · Scientific and Technical Information Processing · doi:10.3103/s0147688210020097 · Cited by 48 · see citing works
Valério, F. A. M., Guimarães, T. G., Prates, R. O., & Candello, H. C. D. S. P. (2017) · Brazilian Symposium on Human Factors in Computing Systems (IHC) · doi:10.1145/3160504.3160544 · Cited by 44 · see citing works
Multimodal Dialogue for Ambient Intelligence and Smart Environments
López-Cózar, R., & Callejas, Z. (2009) · Springer eBooks · doi:10.1007/978-0-387-93808-0_21 · Cited by 43 · see citing works
Fadhil, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.09100 · Cited by 43 · see citing works
How Software Developers Mitigate Collaboration Friction with ChatbotsPreprint
Lebeuf, C., Storey, M.-A. D., & Zagalsky, A. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.07011 · Cited by 40 · see citing works
Lee, M., Lucas, G., Mell, J., Johnson, E., & Gratch, J. S. (2019) · ACM International Conference on Intelligent Virtual Agents (IVA) · doi:10.1145/3308532.3329465 · Cited by 33 · see citing works
Chatbots for troubleshooting: A survey
Thorne, C. (2017) · Language and Linguistics Compass · doi:10.1111/lnc3.12253 · Cited by 32 · see citing works
Social Practice: Becoming Enculturated in Human-Computer Interaction
Cassell, J. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-02713-0_32 · Cited by 28 · see citing works
The Impact of the Gricean Maxims of Quality, Quantity and Manner in Chatbots
Jacquet, B., Hullin, A., Baratgin, J., & Jamet, F. (2019) · International Conference on Information and Digital Technologies (IDT) · doi:10.1109/dt.2019.8813473 · Cited by 27 · see citing works
ParlAmI: A Multimodal Approach for Programming Intelligent Environments
Stefanidi, E., Foukarakis, M., Arampatzis, D., Korozi, M., Leonidis, A., & Antona, M. (2019) · Technologies · doi:10.3390/technologies7010011 · Cited by 21 · see citing works
Chatbots' Greetings to Human-Computer CommunicationPreprint
Pereira, M. J., Coheur, L., Fialho, P., & Ribeiro, R. (2016) · arXiv (Cornell University) · doi:10.4230/oasics.slate.2019.14 · Cited by 19 · see citing works
The Gricean Maxims of Quantity and of Relation in the Turing Test
Jacquet, B., Baratgin, J., & Jamet, F. (2018) · Conference on Human System Interactions · doi:10.1109/hsi.2018.8431328 · Cited by 18 · see citing works
Why to create personalities for synthetic actors
Petta, P., & Trappl, R. (1997) · Lecture notes in computer science · doi:10.1007/bfb0030566 · Cited by 13 · see citing works
Tegos, S. D., Demetriadis, S., & Tsiatsos, Τ. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-39583-8_27 · Cited by 13 · see citing works
Persuasive Conversational Agent with Persuasion Tactics
Narita, T., & Kitamura, Y. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-13226-1_4 · Cited by 12 · see citing works
Ayedoun, E., Hayashi, Y., & Seta, K. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-61425-0_40 · Cited by 12 · see citing works
Towards improving the performance of chat oriented dialogue system
Jiang, R., & Banchs, R. E. (2017) · International Conference on Asian Language Processing · doi:10.1109/ialp.2017.8300537 · Cited by 10 · see citing works
Having an Animated Coffee with a Group of Chatbots from the 19 th Century
Candello, H. C. D. S. P., Pinhanez, C. S., Pichiliani, M. C., Guerra, M. A., & de Bayser, M. G. (2018) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3170427.3186519 · Cited by 10 · see citing works
Extending an Educational Math Game with a Pedagogical Conversational Agent: Facing Design Challenges
Sjödén, B., Silvervarg, A., Haake, M., & Gulz, A. (2011) · Communications in computer and information science · doi:10.1007/978-3-642-20074-8_10 · Cited by 8 · see citing works
Dohsaka, K., Asai, R., Higashinaka, R., Minami, Y., & Maeda, E. (2014) · IEICE Transactions on Information and Systems · doi:10.1587/transinf.e97.d.2147 · Cited by 8 · see citing works
Benjamin Franklin’s Decision Method is Acceptable and Helpful with a Conversational Agent
Mäurer, D., & Weihe, K. (2015) · Smart innovation, systems and technologies · doi:10.1007/978-3-319-19830-9_10 · Cited by 8 · see citing works
Tamayo-Moreno, S., & Pérez-Marín, D. (2016) · International Symposium on Computers in Education · doi:10.1109/siie.2016.7751819 · Cited by 8 · see citing works
A Hybrid Architecture for Multi-Party Conversational SystemsPreprint
de Bayser, M. G., Cavalin, P., Souza, R., Braz, A., Candello, H. C. D. S. P., Pinhanez, C. S., & Briot, J.-P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.01214 · Cited by 8 · see citing works
Towards Socialized Machines: Emotions and Sense of Humour in Conversational Agents
Ptaszynski, M. E., Dybała, P., Higuhi, S., Shi, W., Rzepka, R., & Araki, K. (2010) · InTech eBooks · doi:10.5772/8384 · Cited by 6 · see citing works
Endowing Virtual Characters with Expressive Conversational Skills
Walker, M. A. (2009) · Lecture notes in computer science · doi:10.1007/978-3-642-04380-2_1 · Cited by 5 · see citing works
Leonidis, A., Antona, M., & Stephanidis, C. (2017) · Cited by 2 · see citing works
Survey on social characteristics of human-chatbot interaction
Chaves, A. P., & Gerosa, M. A. (2019) · Figshare · doi:10.5281/zenodo.3473357 · Cited by 2 · see citing works
Self-citationСучасний підхід до проблеми виникнення університету як соціокультурного феномену
Aslan (2018) · Electronic Volyn National University Institutional Repository · doi:10.5281/zenodo
Dechesne (2000) · doi:10.1002/1099-0992(200011/12)30:6
Thorson, J. (1993) · doi:10.1002/1097-4679(199311)49:6
Flagged first, then by citations
Research works printed but not linked: 46
- Abdul-Kader S. A., 2015, International Journal of Advanced Computer Science and Applications, 6, 72
- Auerbach C., 2003, Qualitative data: An introduction to coding and analysis
- Augello A., 2017, International conference on internet science, 236
- Baron N. S., 1984, Visible Language, 18, 118
- Chaves A. P., 2018, Acm sigchi conference on human factors in computing systems
- Conrad S., 2009, Register, genre, and style
- De Angeli A., 2005, Proceedings of the joint symposium on virtual social agents, 7
- De Angeli A., 2006, Proceedings of the avi 2006 workshop on gender and interaction: real and virtual women in a male world
- De Angeli A., 2001, Proceedings of the international conference on affective human factors design, london, 467
- De Angeli A., 2001, Interact, 198
- De Souza, C. S., Prates, R. O. & Barbosa, S. D. (1999). A method for evaluating software communicability. In Proceedings of the IHC '99, Art28 (pp. 1–7). Campinas, SP, Brazil. October, 1999. https://www.unicamp.br/~ihc99/Ihc99/AtasIHC99/Atas.html
- Deshpande A., 2017, International Journal of Computer Engineering and Applications. XI(Special issue), 1–7. https://www.ijcea.com/survey-various-chatbot-implementation-techniques/
- Duijst, D. (2017). Can we improve the user experience of chatbots with personalisation [Unpublished master’s thesis]. University of Amsterdam.
- Duijvelshoff W., 2017, Workshop on chatbots and artificial intelligence
- Dyke G., 2013, Intelligent tutoring systems, 531
- Elliott, C. (1994). Research problems in the use of as allow artificial intelligence model of personality and emotion . In Proceedings of Twelfth National Conference on Artificial Intelligence (AAAI-94) (pp. 9–15). The AAAI Press, Menlo Park, California.
- Ferman, M. (2018). Towards best practices for chatbots [Unpublished master’s thesis]. Universidad Villa Rica.
- Gnewuch U., 2017, International conference on information systems 2017, proceedings 1
- Hayashi Y., 2015, International conference on educational data mining (edm)
- Kirakowskim J., O’Donnell, P., Yiu, A., 2009, Human-computer interaction
- Koda T., 2003, IEICE Transactions on Information and Systems, 86, 1369
- Lasek M., 2013, Information Systems in Management, 2, 146
- Li Y., 2017, International joint conference on natural language processing (ijcnlp), 986
- Liao Q. V., 2018, Proceedings of the 2018 chi conference on human factors in computing systems
- Mairesse F., 2009, Can conversational agents express big five personality traits through language?: Evaluating a psychologically-informed language generator
- Masche J., 2017, International conference on computer science, applied mathematics and applications, 212
- Maslowski I., 2017, International conference on natural language and speech processing
- Meany M. M., 2010, International Journal of the Humanities, 8, 129
- Morris T. W., 2002, Artificial intelligence and interactive entertainment, Technical Report SS-02-01, 82
- Nass C., 1994, Computers are social actors, 72
- Neff G., 2016, International Journal of Communication, 10, 17
- Nguyen Q. N., 2018, Twenty-fourth americas conference on information systems – emergent research forum (erf)
- Radziwill N. M., 2017, Software Quality Professional, 19, 25
- Reeves B., 1996, How people treat computers, television, and new media like real people and places
- Ruch W., 1998, The sense of humor: Explorations of a personality characteristic, 3
- Satu, M. S., Parvez, M. H., Shamim-Al-Mamun, 2015, Computer and information engineering (iccie), 2015 1st international conference on, 87
- Schuetzler R. M., 2018, Americas conference on information systems 2018 proceedings
- Shawar, B. A. & Atwell, E. (2007). Chatbots: Are they really useful? Journal for Language Technology and Computational Linguistics , 22 (1), 29–49. GSCL German Society for Computational Linguistics. https://jlcl.org/content/2-allissues/21-Heft1-2007/Bayan_Abu-Shawar_and_Eric_Atwell.pdf
- Silvervarg A., 2013, 6th international joint conference on natural language processing (ijcnlp 2013), 1223
- Thies I. M., 2017, Human-computer interaction–interact, 10513, 441
- Thomson L., 2005, 1st international workshop on innovations in web infrastructure (iwi 2005) co-located with the 14th world- wide web conference (www2005), japan
- Toxtli, C., Monroy-Hernández, A., Cranshaw, J., 2018, Proceedings of the 2018 chi conference on human factors in computing systems, 58
- Walgama M., 2017, KDU international research conference
- Wallis P., 2005, Proceedings of the joint symposium on virtual social agents, 29
- Walther, J. B. (2011). Theories of computer-mediated communication and interpersonal relations. In M. L. Knapp & J. A. Daly (Eds.), The handbook of interpersonal communication. (4th ed., pp. 443–479). Sage.
- Zhu P., 2018, Proceedings of the 27th international conference on computational linguistics: System demonstrations, 108
Cited by
Sorted by citations
Interacting with educational chatbots: A systematic review
Kuhail, M. A., Alturki, N., Alramlawi, S., & Alhejori, K. (2023) · Education and Information Technologies · doi:10.1007/s10639-022-11177-3 · Cited by 841 · see citing works
Menon, D., & Shilpa, K. (2023) · Heliyon · doi:10.1016/j.heliyon.2023.e20962 · Cited by 359 · see citing works
Ma, X., & Huo, Y. (2023) · Technology in Society · doi:10.1016/j.techsoc.2023.102362 · Cited by 368 · see citing works
Rahim, N. I. M., Iahad, N. A., Yusof, A. F., & Al-Sharafi, M. A. (2022) · Sustainability · doi:10.3390/su141912726 · Cited by 310 · see citing works
Ross, S., Martinez, F., Houde, S., Muller, M. J., & Weisz, J. D. (2023) · ACM International Conference on Intelligent User Interfaces (IUI) · doi:10.1145/3581641.3584037 · Cited by 272 · see citing works
Borsci, S., Malizia, A., Schmettow, M., van der Velde, F., Tariverdiyeva, G., Balaji, D., & Chamberlain, A. (2022) · Personal and Ubiquitous Computing · doi:10.1007/s00779-021-01582-9 · Cited by 266 · see citing works
Social companionship with artificial intelligence: Recent trends and future avenues
Chaturvedi, R., Verma, S., Das, R., & Dwivedi, Y. K. (2023) · Technological Forecasting and Social Change · doi:10.1016/j.techfore.2023.122634 · Cited by 244 · see citing works
Perceptions and Needs of Artificial Intelligence in Health Care to Increase Adoption: Scoping Review
Chew, H. S. J., & Achananuparp, P. (2022) · Journal of Medical Internet Research · doi:10.2196/32939 · Cited by 243 · see citing works
Li, M., & Wang, R. (2022) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2022.103209 · Cited by 256 · see citing works
Developing an AI-based chatbot for practicing responsive teaching in mathematics
Lee, D., & Yeo, S. (2022) · Computers & Education · doi:10.1016/j.compedu.2022.104646 · Cited by 210 · see citing works
Jin, S. V., & Youn, S. (2023) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2022.2129277 · Cited by 201 · see citing works
Janson, A. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2023.107954 · Cited by 187 · see citing works
Kumar, J. A. (2021) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-021-00302-w · Cited by 183 · see citing works
Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Khadpe, P., Krishna, R., Fei-Fei, L., Hancock, J. T., & Bernstein, M. S. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415234 · Cited by 183 · see citing works
Conversational Agents: Goals, Technologies, Vision and Challenges
Allouch, M., Azaria, A., & Azoulay, R. (2021) · Sensors · doi:10.3390/s21248448 · Cited by 168 · see citing works
AI Companions Reduce Loneliness
De Freitas, J., Oğuz-Uğuralp, Z., Uğuralp, A. K., & Puntoni, S. (2026) · Journal of Consumer Research · doi:10.1093/jcr/ucaf040 · Cited by 165 · see citing works
Students' adoption of AI-based teacher-bots (T-bots) for learning in higher education
Pillai, R., Sivathanu, B., Metri, B., & Kaushik, N. (2024) · Information Technology & People · doi:10.1108/itp-02-2021-0152 · Cited by 176 · see citing works
Gkinko, L., & Elbanna, A. R. (2022) · Information Technology and People · doi:10.1108/itp-04-2021-0328 · Cited by 167 · see citing works
The User Experience of ChatGPT: Findings from a Questionnaire Study of Early Users
Skjuve, M. B., Følstad, A., & Brandtzæg, P. B. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597144 · Cited by 152 · see citing works
Cyber Shopping Beyond Boundaries: The Metaverse Revolution in e‐Commerce and Consumer Behavior
Jafar, R. M. S., Jabeen, M., Hussain, S., Niu, B., Sham, R. B., & Al‐Adwan, A. S. (2025) · Human Behavior and Emerging Technologies · doi:10.1155/hbe2/5559234 · Cited by 148 · see citing works
A survey on XAI and natural language explanations
Cambria, E., Malandri, L., Mercorio, F., Mezzanzanica, M., & Nobani, N. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2022.103111 · Cited by 131 · see citing works
Depounti, I., Saukko, P. M., & Natale, S. (2022) · Media Culture & Society · doi:10.1177/01634437221119021 · Cited by 137 · see citing works
Schöbel, S., Schmitt, A., Benner, D., Saqr, M., Janson, A., & Leimeister, J. M. (2024) · Information Systems Frontiers · doi:10.1007/s10796-023-10375-9 · Cited by 127 · see citing works
Song, M., Zhang, H., Xing, X., & Duan, Y. (2023) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2023.103323 · Cited by 131 · see citing works
Designing trust: The formation of employees’ trust in conversational AI in the digital workplace
Gkinko, L., & Elbanna, A. R. (2023) · Journal of Business Research · doi:10.1016/j.jbusres.2023.113707 · Cited by 136 · see citing works
Zhang, B., Zhu, Y., Deng, J., Zheng, W., Liu, Y., Wang, C., & Zeng, R. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2124345 · Cited by 127 · see citing works
Terblanche, N., & Kidd, M. (2022) · Sage Open · doi:10.1177/21582440221096136 · Cited by 120 · see citing works
Yang, Z., Xu, X., Yao, B., Rogers, E., Zhang, S., Intille, S., Shara, N., Gao, G. G., & Wang, D. (2024) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3659625 · Cited by 120 · see citing works
“In addition, failure of the CA such as voice recognition issues (Section 5.2.3) [27, 83], should also be addressed to ensure the information accuracy.”
BackgroundInfluentialA comprehensive survey of large language models and multimodal large language models in medicine
Xiao, H., Zhou, F., Liu, X., Liu, T., Ли, Ж., Liu, X., & Huang, X. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102888 · Cited by 130 · see citing works
Orden-Mejía, M. A., & Huertas, A. (2021) · Current Issues in Tourism · doi:10.1080/13683500.2021.1997942 · Cited by 123 · see citing works
Hari, H., Iyer, R., & Sampat, B. H. (2021) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2021.1988487 · Cited by 111 · see citing works
UX Research on Conversational Human-AI Interaction: A Literature Review of the ACM Digital Library
Zheng, Q., Tang, Y., Liu, Y., Liu, W., & Huang, Y. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501855 · Cited by 114 · see citing works
Wutz, M., Hermes, M., Winter, V., & Köberlein–Neu, J. (2023) · Journal of Medical Internet Research · doi:10.2196/46548 · Cited by 111 · see citing works
Towards User-Centric Guidelines for Chatbot Conversational Design
Silva, G. R. S., & Canedo, E. D. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2118244 · Cited by 111 · see citing works
How do consumers react to chatbots' humorous emojis in service failures
Liu, D., Lv, Y., & Huang, W. (2023) · Technology in Society · doi:10.1016/j.techsoc.2023.102244 · Cited by 95 · see citing works
Li, Q., Luximon, Y., & Zhang, J. (2023) · Journal of Medical Internet Research · doi:10.2196/44479 · Cited by 102 · see citing works
Ling, E. C., Tussyadiah, I. P., Liu, A., & Stienmetz, J. L. (2023) · Journal of Travel Research · doi:10.1177/00472875231217899 · Cited by 107 · see citing works
Effects of Anthropomorphic Design Cues of Chatbots on Users’ Perception and Visual Behaviors
Chen, J., Guo, F., Ren, Z., Li, M., & Ham, J. R. C. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2193514 · Cited by 96 · see citing works
The Ethics of Using Artificial Intelligence in Qualitative Research
Marshall, D. T., & Naff, D. (2024) · Journal of Empirical Research on Human Research Ethics · doi:10.1177/15562646241262659 · Cited by 112 · see citing works
MarkBot – A Language Model-Driven Chatbot for Interactive Marketing in Post-Modern World
Kushwaha, A. K., & Kar, A. (2021) · Information Systems Frontiers · doi:10.1007/s10796-021-10184-y · Cited by 85 · see citing works
State-of-the-Art Human-Computer-Interaction in Metaverse
Lyu, Z. (2023) · International journal of human computer interactions · doi:10.1080/10447318.2023.2248833 · Cited by 82 · see citing works
Izadi, S., & Forouzanfar, M. (2024) · AI · doi:10.3390/ai5020041 · Cited by 102 · see citing works
The Use of Chatbots in Digital Business Transformation: A Systematic Literature Review
Miklošík, A., Evans, N., & Qureshi, A. M. A. (2021) · IEEE Access · doi:10.1109/access.2021.3100885 · Cited by 89 · see citing works
Talking to a bot or a wall? How chatbots vs. human agents affect anticipated communication quality
Zhou, Q., Li, B., Han, L., & Jou, M. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2023.107674 · Cited by 93 · see citing works
Xu, Y., Niu, N., & Zhao, Z. (2023) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2023.103417 · Cited by 91 · see citing works
Understanding EFL students’ chatbot-assisted argumentative writing: An activity theory perspective
Guo, K., Li, Y., Li, Y., & Chu, S. K. W. (2023) · Education and Information Technologies · doi:10.1007/s10639-023-12230-5 · Cited by 83 · see citing works
Toward a design theory for virtual companionship
Strohmann, T., Siemon, D., Khosrawi-Rad, B., & Robra-Bissantz, S. (2022) · Human-Computer Interaction · doi:10.1080/07370024.2022.2084620 · Cited by 89 · see citing works
Service robots with (perceived) theory of mind: An examination of humans’ reactions
Söderlund, M. (2022) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2022.102999 · Cited by 83 · see citing works
AI Companions Reduce Loneliness
De Freitas, J., Uğuralp, A. K., Uğuralp, Z., & Puntoni, S. (2024) · doi:10.2139/ssrn.4893097 · Cited by 80 · see citing works
Ju, J., Meng, Q., Sun, F., Liu, L., & Singh, S. R. (2023) · Government Information Quarterly · doi:10.1016/j.giq.2022.101785 · Cited by 77 · see citing works
Yang, B., Sun, Y., & Shen, X. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103257 · Cited by 75 · see citing works
Cheng, X., Qiao, L., Yang, B., & Li, Z. (2024) · Internet Research · doi:10.1108/intr-06-2022-0402 · Cited by 76 · see citing works
Jo, E., Jeong, Y., Park, S., Epstein, D. A., & Kim, Y. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642420 · Cited by 75 · see citing works
Dekkal, M., Arcand, M., Tep, S. P., Rajaobelina, L., & Ricard, L. (2023) · Journal of Financial Services Marketing · doi:10.1057/s41264-023-00230-y · Cited by 75 · see citing works
Ha, J., Jeon, H., Han, D. S., Seo, J., & Oh, C. (2024) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642472 · Cited by 76 · see citing works
Leo-Liu, J. (2022) · Computers in Human Behavior · doi:10.1016/j.chb.2022.107620 · Cited by 89 · see citing works
Zhou, C. Y., & Chang, Q. (2024) · Journal of Retailing and Consumer Services · doi:10.1016/j.jretconser.2024.103779 · Cited by 72 · see citing works
A Conversation-Driven Approach for Chatbot Management
Santos, G. A., de Andrade, G. G., Silva, G. R. S., Duarte, F. C. M., da Costa, J. P. C. L., & de Sousa, R. T. (2022) · IEEE Access · doi:10.1109/access.2022.3143323 · Cited by 68 · see citing works
Valtolina, S., & Hu, L. (2021) · Biannual Conference of the Italian SIGCHI Chapter (CHItaly) · doi:10.1145/3464385.3464726 · Cited by 63 · see citing works
A survey on chatbots and large language models: Testing and evaluation techniques
Singh, S. U., & Namin, A. S. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100128 · Cited by 71 · see citing works
Moradbakhti, L., Schreibelmayr, S., & Mara, M. (2022) · Frontiers in Psychology · doi:10.3389/fpsyg.2022.855091 · Cited by 67 · see citing works
Hu, J., Huang, Y., Hu, X., & Xu, Y. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3205919 · Cited by 61 · see citing works
Siqueira, M. A. D. S., Müller, B. C. N., & Bosse, T. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2175158 · Cited by 62 · see citing works
A survey on near-human conversational agents
Singh, S., & Beniwal, H. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.10.013 · Cited by 63 · see citing works
Jin, E., & Eastin, M. S. (2022) · Journal of Research in Interactive Marketing · doi:10.1108/jrim-03-2022-0089 · Cited by 61 · see citing works
Intelligent Virtual Laboratory Development and Implementation using the RASA Framework
Josphineleela, R., Kaliappan, S., Natrayan, L., & Bhatt, U. M. (2023) · International Conference on Computing Methodologies and Communication (ICCMC) · doi:10.1109/iccmc56507.2023.10083701 · Cited by 55 · see citing works
Gaczek, P., Leszczyński, G., & Mouakher, A. (2023) · Industrial Marketing Management · doi:10.1016/j.indmarman.2023.09.007 · Cited by 63 · see citing works
Social Chatbot: My Friend in My Distress
Ali, F., Zhang, Q., Tauni, M. Z., & Shahzad, K. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2150745 · Cited by 58 · see citing works
Huang, M., & Ki, E. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2290378 · Cited by 58 · see citing works
Anthropomorphism in artificial intelligence: a game-changer for brand marketing
Gomes, S., Lopes, J. M., & Nogueira, E. (2025) · Future Business Journal · doi:10.1186/s43093-025-00423-y · Cited by 52 · see citing works
Yang, T., & Chen, J. (2022) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2022.100119 · Cited by 51 · see citing works
Exploring how politeness impacts the user experience of chatbots for mental health support
Bowman, R., Cooney, O., Newbold, J. W., Thieme, A., Clark, L., Doherty, G. J., & Cowan, B. R. (2023) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2023.103181 · Cited by 57 · see citing works
Understanding users’ perspectives on mobile apps for anxiety management
Balaskas, A., Schueller, S. M., Cox, A. L., & Doherty, G. J. (2022) · Frontiers in Digital Health · doi:10.3389/fdgth.2022.854263 · Cited by 49 · see citing works
Towards Human-centered Proactive Conversational Agents
Deng, Y., Liao, L., Zheng, Z., Yang, G. H., & Chua, T. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657843 · Cited by 51 · see citing works
Tan, S.-M., & Liew, T. W. (2022) · Human Behavior and Emerging Technologies · doi:10.1155/2022/2501538 · Cited by 54 · see citing works
Setlur, V., & Tory, M. K. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501972 · Cited by 53 · see citing works
Enhancing service recovery satisfaction with chatbots: The role of humor and informal language
Shams, G., Kim, K. K., & Kim, K. (2024) · International Journal of Hospitality Management · doi:10.1016/j.ijhm.2024.103782 · Cited by 55 · see citing works
Yim, M. C. (2023) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2023.2234114 · Cited by 51 · see citing works
Measuring perceived empathy in dialogue systems
Concannon, S. J., & Tomalin, M. (2023) · AI & Society · doi:10.1007/s00146-023-01715-z · Cited by 51 · see citing works
Sikström, P., Valentini, C., Sivunen, A. E., & Kärkkäinen, T. (2024) · Computers & Education · doi:10.1016/j.compedu.2024.105140 · Cited by 58 · see citing works
Liu, I., Liu, F., Xiao, Y., Huang, Y., Wu, S., & Ni, S. (2025) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2300015 · Cited by 44 · see citing works
Does Chatbot Language Formality Affect Users’ Self-Disclosure?
Cox, S. R., & Ooi, W. T. (2022) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3543829.3543831 · Cited by 48 · see citing works
Rese, A., & Tränkner, P. (2023) · International Journal of Information Management · doi:10.1016/j.ijinfomgt.2023.102699 · Cited by 47 · see citing works
Park, Y., Kim, J., Jiang, Q., & Kim, K. H. (2024) · Journal of Global Scholars of Marketing Science · doi:10.1080/21639159.2024.2362654 · Cited by 45 · see citing works
Heng, S., & Zhang, Z. (2025) · Psychology Research and Behavior Management · doi:10.2147/prbm.s531805 · Cited by 54 · see citing works
Desirable or Distasteful? Exploring Uncertainty in Human-Chatbot Relationships
Pan, S., Cui, J., & Mou, Y. (2024) · International Journal of Human–Computer Interaction · doi:10.1080/10447318.2023.2256554 · Cited by 44 · see citing works
Modeling users’ satisfaction and visit intention using AI-based chatbots
Orden-Mejía, M. A., Carvache‐Franco, M., Huertas, A., Carvache‐Franco, O., & Carvache‐Franco, W. (2023) · PLoS ONE · doi:10.1371/journal.pone.0286427 · Cited by 55 · see citing works
Chavez‐Yenter, D., Kimball, K. E., Kohlmann, W. K., Chambers, R. L., Bradshaw, R. L., Espinel, W., Flynn, M. C., Gammon, A., Goldberg, E., Hagerty, K. J., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/29447 · Cited by 43 · see citing works
Gumusel, E. (2024) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.24898 · Cited by 50 · see citing works
Khan, M. I., Fatima, J. K., Bahmannia, S., Chatrath, S. K., Dale, N. F., & Johns, R. (2025) · Journal of Service Theory and Practice · doi:10.1108/jstp-10-2023-0282 · Cited by 43 · see citing works
Investigating the Effects of Perceived Teammate Artificiality on Human Performance and Cognition
Schelble, B. G., Flathmann, C., McNeese, N. J., O’Neill, T., Pak, R., & Namara, M. (2022) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2022.2085191 · Cited by 42 · see citing works
Wu, P. F., Summers, C., Panesar, A., Kaura, A., & Li, Z. (2024) · JMIR Human Factors · doi:10.2196/51086 · Cited by 43 · see citing works
A year of generative AI in English language teaching and learning - A case study
Hınız, G. (2024) · Journal of Research on Technology in Education · doi:10.1080/15391523.2024.2404132 · Cited by 42 · see citing works
Design Foundations for AI Assisted Decision Making: A Self Determination Theory Approach
De Vreede, T., Raghavan, M., & De Vreede, G.-J. (2021) · Proceedings of the Annual Hawaii International Conference on System Sciences · doi:10.24251/hicss.2021.019 · Cited by 42 · see citing works
Nguyen, T. H., Waizenegger, L., & Techatassanasoontorn, A. (2021) · Information Systems Frontiers · doi:10.1007/s10796-021-10212-x · Cited by 39 · see citing works
Kim, J., Muhic, J., Robert, L., & Park, S. Y. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3502116 · Cited by 41 · see citing works
Lee, S., Park, G., & Chung, J. (2023) · Telematics and Informatics · doi:10.1016/j.tele.2023.102009 · Cited by 41 · see citing works
Use of chatbots for customer service in MSMEs
Cordero, J., Barba-Guamán, L., & Guamán, F. (2022) · Applied Computing and Informatics · doi:10.1108/aci-06-2022-0148 · Cited by 39 · see citing works
Sheng, M. L., Natália, N., & Rusfian, E. Z. (2024) · Psychology and Marketing · doi:10.1002/mar.22165 · Cited by 43 · see citing works
Calvaresi, D., Calbimonte, J.-P., Siboni, E., Eggenschwiler, S., Manzo, G., Hilfiker, R., & Schumacher, M. (2021) · Electronics · doi:10.3390/electronics10060666 · Cited by 39 · see citing works
- Authors
- Chaves, A. P., & Gerosa, M. A.
- Affiliations
- Universidade Tecnológica Federal do Paraná (BR)
- Northern Arizona University (US)
- Corresponding author
- Chaves, Ana Paula
- ORCID
- Chaves, Ana Paula
- Venue
- International Journal of Human–Computer Interaction
- Publisher
- Informa UK Limited
- Published
- 2020-11-08
- Volume
- 37
- Issue
- 8
- Pages
- 729-758
- ISSN
- 1044-7318 (ISSN-L)
- 1532-7590
- OpenAlex
- W2939803556
- Semantic Scholar
- df6ae7c951a4ae2b548c86768cd94be28adee7f3
- Cited by
- 572
- References
- 115
- Citations by year
- 2026: 101 · 2025: 134 · 2024: 118 · 2023: 104 · 2022: 74 · 2021: 36 · 2020: 3 · 2019: 2
- FWCI
- 59.25
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- International Journal of Human-Computer Interaction (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- chatbots, human-chatbot interaction, social characteristics, chatbot design, conversation, text-based chatbots, user expectations, conceptual model
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-09.
Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-09.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
