What Makes a Good Conversation?: Challenges in Designing Truly Conversational Agents
Open accessThe DOI matches its Crossref record; 51 of the 51 references it cites were found in a registry or an index.
Abstract
Conversational agents promise conversational interaction but fail to deliver. Efforts often emulate functional rules from human speech, without considering key characteristics that conversation must encapsulate. Given its potential in supporting long-term human-agent relationships, it is paramount that HCI focuses efforts on delivering this promise. We aim to understand what people value in conversation and how this should manifest in agents. Findings from a series of semi-structured interviews show people make a clear dichotomy between social and functional roles of conversation, emphasising the long-term dynamics of bond and trust along with the importance of context and relationship stage in the types of conversations they have. People fundamentally questioned the need for bond and common ground in agent communication, shifting to more utilitarian definitions of conversational qualities. Drawing on these findings we discuss key challenges for conversational agent design, most notably the need to redefine the design parameters for conversational agent interaction.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“People generally expect to have functional conversations with voice assistants [11].”
From A Mixed-Methods Approach to Understanding User Trust after Voice Assistant Failures (2023) · cites this paper as [11]
The cited source says what the claim attributes to it.
In the citing paper
“As extensively noted in VUI literature, VUIs are not “conversational” in nature [24,25,31,36,45,83].”
From OK Google, Let's Learn: Using Voice User Interfaces for Informal Self-Regulated Learning of Health Topics among Younger and Older Adults (2023) · cites this paper as [25]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Whereas, we found that the challenges our participants experienced were more elementary.”
From Exploring How Older Adults Use a Smart Speaker–Based Voice Assistant in Their First Interactions: Qualitative Study (2021) · cites this paper as [31]
Experimental — accuracy not yet measuredIn the citing paper
“Commercial Voice interfaces adopt a request-response mechanism, and thus are transactional in nature [15,40].”
From Using Experience-Based Participatory Approach to Design Interactive Voice User Interfaces for Delivering Physical Activity Programs with Older Adults (2023) · cites this paper as [15]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414 · cited 1×
“r demographics. They were then debriefed and thanked for participating. The audio recordings were transcribed and analysed in a systematic qualitative interpretation using Inductive Thematic Analysis [9]. Initial coding was conducted by two researchers working independently. We began with an inductive approach, then g…”
MethodPoliteness : Some Universals in Language Usage
Brown, P. (1987) · Cited by 12,120
Politeness: Some Universals in Language Usage
Brown, P., Levinson, S. C., & Gumperz, J. J. (1987) · Cambridge University Press eBooks · doi:10.1017/cbo9780511813085 · Cited by 10,438
Clark, H. H., & Brennan, S. E. (1991) · Perspectives on socially shared cognition. · doi:10.1037/10096-006 · Cited by 4,555 · cited 1×
“Although this brings an illusion of mutual shared knowledge integral to common ground [16, 17], participants clearly do not see this as being collaboratively built, negotiated and updated during agent dialogue, juxtaposing grounding processes in human conversation [18].”
BackgroundEmotion and sociable humanoid robots
Breazeal, C. (2003) · International Journal of Human-Computer Studies · doi:10.1016/s1071-5819(03)00018-1 · Cited by 1,279 · cited 1×
“the best approach to use to develop bond. This could be achieved through exploiting other modalities, especially in more embodied systems (e.g.[30]). Through gesture and facial expressions cues (e.g. [10, 13, 33]) embodiment may even help support speech-based conversation. Limitations and Future Work This paper identi…”
Background(1996) · Medical Entomology and Zoology · Cited by 1,176
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 · cited 5×
“hat conversational agents can and should be capable of performing. These expectations support the notion that an agent is a basic dialogue partner [8] lacking in humanlike conversational capabilities [20, 35, 42]. Our participants personally expressed no desire to build bonds with conversational agents (although they…”
BackgroundResultInfluentialStudies in the Organization of Conversational Interaction
(1978) · Elsevier eBooks · doi:10.1016/c2013-0-11461-4 · Cited by 867
2 On the Preferences for Agreement and Contiguity in Sequences in Conversation
Sacks, H. (1987) · Talk and Social Organisation · doi:10.21832/9781800418226-004 · Cited by 861
Voice Interfaces in Everyday Life
Porcheron, M., Fischer, J. E., Reeves, S., & Sharples, S. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174214 · Cited by 717 · cited 11×
“Speaking to agents currently falls short of conversational dialogue [37, 39, 42], ar X iv :1 90 1.”
BackgroundResultInfluentialMcTear, M., Callejas, Z., & Griol, D. (2016) · doi:10.1007/978-3-319-32967-3 · Cited by 594
Socially assistive robotics [Grand Challenges of Robotics]
Tapus, A., Mataric, M., & Scassellati, B. (2007) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2007.339605 · Cited by 547
Relational agents: a model and implementation of building user trust
Bickmore, T., & Cassell, J. (2001) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/365024.365304 · Cited by 479 · cited 1×
“r experience of more conversational interactions with agents. A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts. ECA research [3] showed that users trusted an agent more when small talk was used and…”
Background"Alexa is my new BFF": Social Roles, User Satisfaction, and Personification of the Amazon Echo
Purington, A., Taft, J. G., Sannon, S., Bazarova, N. N., & Taylor, S. H. (2017) · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/3027063.3053246 · Cited by 476
Designing robots for long-term social interaction
Gockley, R., Bruce, A., Forlizzi, J., Michalowski, M., Mundell, A., Rosenthal, S., Sellner, B., Simmons, R., Snipes, K., Schultz, A. C., et al. (2005) · 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2005.1545303 · Cited by 407
"What can i help you with?": infrequent users' experiences of intelligent personal assistants
Cowan, B. R., Pantidi, N., Coyle, D., Morrissey, K., Clarke, P., Al-Shehri, S., Earley, D., & Bandeira, N. (2017) · Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3098279.3098539 · Cited by 351 · cited 5×
“hat conversational agents can and should be capable of performing. These expectations support the notion that an agent is a basic dialogue partner [8] lacking in humanlike conversational capabilities [20, 35, 42]. Our participants personally expressed no desire to build bonds with conversational agents (although they…”
BackgroundResultInfluentialSelf-citationInteraction Ritual: Essays in Face-to-Face Behavior
Goffman, E., & Best, J. (2017) · doi:10.4324/9780203788387 · Cited by 324
Expressive robots in education: varying the degree of social supportive behavior of a robotic tutor
Saerbeck, M., Schut, T., Bartneck, C., & Janse, M. D. (2010) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1753326.1753567 · Cited by 321 · cited 1×
“s have explored the user experience of more conversational interactions with agents. A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts. ECA research [3] showed that users trusted an agent more when s…”
BackgroundUnderstanding the Long-Term Use of Smart Speaker Assistants
Bentley, F., Luvogt, C., Silverman, M., Wirasinghe, R., White, B., & Lottridge, D. (2018) · Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies · doi:10.1145/3264901 · Cited by 316 · cited 1×
“These include checking the weather, setting reminders, calling and messaging, playing music, launching other applications, information seeking, and interacting with Internet of Things (IoT) devices [2, 20, 35, 38, 54].”
BackgroundThe role of expressiveness and attention in human-robot interaction
Bruce, A., Nourbakhsh, I., & Simmons, R. (2003) · Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292) · doi:10.1109/robot.2002.1014396 · Cited by 294 · cited 1×
“the best approach to use to develop bond. This could be achieved through exploiting other modalities, especially in more embodied systems (e.g.[30]). Through gesture and facial expressions cues (e.g. [10, 13, 33]) embodiment may even help support speech-based conversation. Limitations and Future Work This paper identi…”
BackgroundPrivacy Concerns for Use of Voice Activated Personal Assistant in the Public Space
Easwara Moorthy, A., & Vu, K.-P. L. (2015) · International Journal of Human-Computer Interaction · doi:10.1080/10447318.2014.986642 · Cited by 250 · cited 1×
“engage with IPAs in public [20, 35], noting social embarrassment and awkwardness [1, 20]. Users have fewer concerns divulging private information when using VUIs in private compared to social spaces [1, 24]. We identify a clear distinction between human and agent based conversation in terms of its perceived norms, rul…”
BackgroundLooije, R., Neerincx, M. A., & Cnossen, F. (2010) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2009.08.007 · Cited by 243 · cited 1×
“The accommodation of social conversations is proposed as a critical factor in developing trust in a social agent [34].”
BackgroundThe role of beliefs in lexical alignment: Evidence from dialogs with humans and computers
Branigan, H. P., Pickering, M. J., Pearson, J., McLean, J. F., & Brown, A. (2011) · Cognition · doi:10.1016/j.cognition.2011.05.011 · Cited by 231 · cited 1×
“These expectations support the notion that an agent is a basic dialogue partner [8] lacking in humanlike conversational capabilities [20, 35, 42].”
BackgroundGrooming, Gossip, and the Evolution of Language
Turkel, W. J., & Dunbar, R. (1999) · Language · doi:10.2307/417520 · Cited by 221 · cited 1×
“chievement of the transaction’s purpose. The aim of more social conversation is not to complete a task as such, but to build, maintain and strengthen positive relations with one or more interlocutors [23, 36]. Social conversation ranges from small talk and social greetings to longer interactions. Examples include talk…”
BackgroundResponse to a relational agent by hospital patients with depressive symptoms
Bickmore, T. W., Mitchell, S. E., Jack, B. W., Paasche-Orlow, M. K., Pfeifer, L. M., & O’Donnell, J. (2010) · Interacting with Computers · doi:10.1016/j.intcom.2009.12.001 · Cited by 218 · cited 1×
“A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts.”
BackgroundA Simplest Systematics for the Organization of Turn-Taking for Conversation
Sacks, H., Schegloff, E., & Jefferson, G. (2015) · Sotsiologicheskoe Obozrenie / Russian Sociological Review · doi:10.17323/1728-192x-2015-1-142-202 · Cited by 211
A conversational robot in an elderly care center: an ethnographic study
Sabelli, A. M., Kanda, T., & Hagita, N. (2011) · Proceedings of the 6th international conference on Human-robot interaction · doi:10.1145/1957656.1957669 · Cited by 187 · cited 2×
“as important to long term rapport building and use [53]. The accommodation of social conversations is proposed as a critical factor in developing trust in a social agent [34]. Work by Sabelli et al. [47] found that people were open to speaking about personal matters with a conversational robot, using it as an emotiona…”
BackgroundAbdolrahmani, A., Kuber, R., & Branham, S. M. (2018) · Proceedings of the 20th International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3234695.3236344 · Cited by 172 · cited 1×
“discuss conversationally with agents may differ markedly in private and public settings. Current users are unlikely to engage with IPAs in public [20, 35], noting social embarrassment and awkwardness [1, 20]. Users have fewer concerns divulging private information when using VUIs in private compared to social spaces […”
BackgroundDesigning Relational Agents as Long Term Social Companions for Older Adults
Vardoulakis, L. P., Ring, L., Barry, B., Sidner, C. L., & Bickmore, T. (2012) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-33197-8_30 · Cited by 166 · cited 1×
“A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts.”
BackgroundAcceptance and usability of a relational agent interface by urban older adults
Bickmore, T. W., Caruso, L., & Clough-Gorr, K. (2005) · CHI '05 Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/1056808.1056879 · Cited by 142 · cited 1×
“A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts.”
BackgroundMuseum guide robot based on sociological interaction analysis
Kuno, Y., Sadazuka, K., Kawashima, M., Yamazaki, K., Yamazaki, A., & Kuzuoka, H. (2007) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1240624.1240804 · Cited by 134 · cited 1×
“[10, 13, 33]) embodiment may even help support speech-based conversation.”
BackgroundBickmore, T. W., & Picard, R. W. (2004) · CHI '04 Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/985921.986097 · Cited by 122 · cited 1×
“nce, research on ECAs and social robotics have explored the user experience of more conversational interactions with agents. A number of these agents have been developed for contexts including health [6, 7], elderly care [5, 55], education [50], customer service [3] and workplace [29] contexts. ECA research [3] showed…”
BackgroundThe Social Function of Humor in Interpersonal Relationships
Ziv, A. (2009) · Society · doi:10.1007/s12115-009-9283-9 · Cited by 120 · cited 2×
“A number of these attributes and their purposes align with issues discussed in existing linguistics literature [12, 16, 30, 31, 57].”
BackgroundEnvisioning ubiquitous computing
Reeves, S. (2012) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/2207676.2208278 · Cited by 114 · cited 1×
“Future research should explore ways to get users to focus on envisioning longer, sequential interactions where conversational capabilities are more sophisticated [44, 46].”
BackgroundKidwell, M. (2000) · Issues in Applied Linguistics · doi:10.5070/l4111005024 · Cited by 112
Thompson, S. A. (1990) · Language · doi:10.2307/414637 · Cited by 100 · cited 2×
“ckground in HCI, with experience in conducting qualitative data analyses. In the following section we present the findings from our analysis. 4Findings Purposes of Conversation Echoing the literature [15], two broad purposes for conversation were clearly shown in the data. These reflected social and transactional goal…”
BackgroundAdvances in Natural Multimodal Dialogue Systems
(2005) · Text, Speech and Language Technology · doi:10.1007/1-4020-3933-6 · Cited by 99
At home with agents: exploring attitudes towards future smart energy infrastructures
Rodden, T. A., Fischer, J. E., Pantidi, N., Bachour, K., & Moran, S. (2013) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/2470654.2466152 · Cited by 87
Self-citationChildren asking questions: speech interface reformulations and personification preferences
Yarosh, S., Thompson, S., Watson, K., Chase, A., Senthilkumar, A., Yuan, Y., & Brush, A. J. B. (2018) · Proceedings of the 17th ACM Conference on Interaction Design and Children · doi:10.1145/3202185.3202207 · Cited by 84 · cited 1×
“have different opinions towards agent-based conversations. Recent studies have indicated that certain users groups tend to anthropomorphise their devices, particularly older adults and children (e.g.[43, 56]). Users such as these may perceive conversation with machines differently to the sample population in this pape…”
BackgroundIs Spoken Language All-or-Nothing? Implications for Future Speech-Based Human-Machine Interaction
Moore, R. K. (2017) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-10-2585-3_22 · Cited by 66 · cited 2×
“perceived status between agent and user where the agent was considered a user-controlled tool rather than a potential companion or social equal. This, in tandem with perceptions of functional ability [39] may restrict the types of conversations that users perceive as appropriate or possible to have with an agent at pr…”
BackgroundDialogues with Social Robots: Enablements, Analyses, and Evaluation
Jokinen, K., & Wilcock, G. (2016) · Lecture notes in electrical engineering · doi:10.1007/978-981-10-2585-3 · Cited by 56
ON MODELINGWhat is conversation, and how can we design for it?
Dubberly, H., & Pangaro, P. (2009) · interactions · doi:10.1145/1551986.1551991 · Cited by 44
Alana: Social Dialogue using an Ensemble Model and a Ranker trained on User Feedback
Papaioannou, I. A., Curry, A. C., Part, J. L., Shalyminov, I., Xu, X., Yu, Y., Dušek, O., Rieser, V., & Lemon, O. (2017) · Edinburgh Napier Research Repository (Edinburgh Napier University) · Cited by 30
Designing Speech, Acoustic and Multimodal Interactions
Munteanu, C., Irani, P., Oviatt, S., Aylett, M., Penn, G., Pan, S., Sharma, N., Rudzicz, F., Gomez, R., Cowan, B., et al. (2017) · Proceedings of the 2017 CHI Conference Extended Abstracts on Human Factors in Computing Systems · doi:10.1145/3027063.3027086 · Cited by 25 · cited 1×
“The recent popularity of IPA devices like Amazon Echo and Google Home has generated considerable interest in the HCI community [40, 42].”
BackgroundSelf-citationExplorations in multiparty casual social talk and its relevance for social human machine dialogue
Gilmartin, E., Cowan, B. R., Vogel, C. M., & Campbell, N. (2018) · Journal on Multimodal User Interfaces · doi:10.1007/s12193-018-0274-2 · Cited by 19 · cited 1×
“This is a far cry from the elaborative, contextual social talk seen in human conversation [28].”
BackgroundSelf-citationSocial Boundaries of Appropriate Speech in HCI: A Politeness Perspective
Clark, L. (2018) · Electronic workshops in computing · doi:10.14236/ewic/hci2018.76 · Cited by 18 · cited 1×
“on or social equal. This, in tandem with perceptions of functional ability [39] may restrict the types of conversations that users perceive as appropriate or possible to have with an agent at present [19]. Critically, our findings suggest that social aspects of conversational interaction are currently absent from peop…”
BackgroundSelf-citationSocial talk: making conversation with people and machine
Gilmartin, E., Collery, M., Su, K., Huang, Y., Elias, C., Cowan, B. R., & Campbell, N. (2017) · Proceedings of the 1st ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents · doi:10.1145/3139491.3139494 · Cited by 17 · cited 2×
“Emulating the structures and rules that govern human conversation [27] help generate conversation-like abilities, but they do not guarantee that the important subjective characteristics of conversation are preserved.”
BackgroundSelf-citationMultifaceted Engagement in Social Interaction with a Machine: The JOKER Project
Devillers, L. Y., Rosset, S., Duplessis, G. D., Béchade, L., Yemez, Y., Türker, B. B., Sezgin, T. M., Erzin, E., Haddad, K. E., Dupont, S., et al. (2018) · International Conference on Automatic Face and Gesture Recognition · doi:10.1109/fg.2018.00110 · Cited by 16 · cited 2×
“To address the current deficit in conversational ability, developers have largely focused on imbuing agents with more human-like conversational qualities such as social talk [4, 52] and humour [21].”
BackgroundSelf-citationIntroducing ADELE: a personalized intelligent companion
Spillane, B., Gilmartin, E., Saam, C., Su, K., Cowan, B. R., Lawless, S., & Wade, V. (2017) · ACM SIGCHI International Workshop on Investigating Social Interactions with Artificial Agents (ISIAA) · doi:10.1145/3139491.3139492 · Cited by 14 · cited 2×
“To address the current deficit in conversational ability, developers have largely focused on imbuing agents with more human-like conversational qualities such as social talk [4, 52] and humour [21].”
BackgroundSelf-citationSome conversational challenges of talking with machines
Reeves, S. (2017) · Repository@Nottingham (University of Nottingham) · Cited by 11
Proceedings 1990 IEEE International Conference on Robotics and Automation (Cat. No.90CH2876-1)
(1990) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.1990.125924 · Cited by 8
Research works printed but not linked: 10
- 10.1017/CBO9780511805226 · DOI · Paper page
- H.H. Clark. 1996. Using Language. Cambridge University Press. https: //books.google.ie/books?id=DiWBGOP-YnoC
- Herbert H Clark. 1992. Arenas of language use. University of Chicago Press.
- Rachel Gockley, Allison Bruce, Jodi Forlizzi, Marek Michalowski, Anne Mundell, Stephanie Rosenthal, Brennan Sellner, Reid Simmons, Kevin Snipes, Alan C Schultz, and others. 2005. Designing robots for longterm social interaction. In Intelligent Robots and Systems, 2005.(IROS 2005). 2005 IEEE/RSJ International Conference on. IEEE, 1338--1343.
- Adam Jaworski. 2014. Silence and small talk. In Small talk. Routledge, 130--152.
- Bronislaw Malinowski. 1994. The problem of meaning in primitive languages. Language and literacy in social practice: A reader (1994), 1--10.
- 10.5555/2965050 · doi:10.5555/2965050
- Rishabh Mehrotra, A Hassan Awadallah, AE Kholy, and Imed Zitouni. 2017. Hey Cortana! Exploring the use cases of a Desktop based Digital Assistant. In SIGIR 1st International Workshop on Conversational Approaches to Information Retrieval (CAIR'17), Vol. 4.
- Klaus P. Schneider. 1988. Small talk: Analyzing phatic discourse. Vol. 1. Hitzeroth.
- Janice Y. Tsai, Tawfq Ammaria, Abraham Wallin, and Jofsh Kaye. 2018. Alexa, play some music: Categorization of Alexa Commands. In Workshop on Voice-based Conversational UX Studies and Design (CHI'18).
Cited by
My Chatbot Companion - a Study of Human-Chatbot Relationships
Skjuve, M., Følstad, A., Fostervold, K. I., & Brandtzaeg, P. B. (2021) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2021.102601 · Cited by 797
“Similarly, Clark et al. (2019) did not find evidence of relationship formation between users and chatbots and attributed this to the strictly task-oriented nature of interactions with conversational agents such as Alexa.”
Background"I Hear You, I Feel You": Encouraging Deep Self-disclosure through a Chatbot
Lee, Y.-C., Yamashita, N., Huang, Y., & Fu, W. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376175 · Cited by 339
A longitudinal study of human–chatbot relationships
Skjuve, M., Følstad, A., Fostervold, K. I., & Brandtzaeg, P. B. (2022) · International Journal of Human-Computer Studies · doi:10.1016/j.ijhcs.2022.102903 · Cited by 253
“…people can view conversational agents as friends, the features of such agents are typically highly task-oriented and do not exhibit the relational qualities of social chatbots, such as features for establishing common ground, sharing history, and allowing for personal intimacy (Clark et al., 2019).”
BackgroundHuman-level play in the game of Diplomacy by combining language models with strategic reasoning
Meta Fundamental AI Research Diplomacy Team (FAIR)†, Bakhtin, A., Brown, N., Dinan, E., Farina, G., Flaherty, C., Fried, D., Goff, A., Gray, J., Hu, H., et al. (2022) · Science · doi:10.1126/science.ade9097 · Cited by 241
Loneliness and suicide mitigation for students using GPT3-enabled chatbots
Maples, B., Cerit, M., Vishwanath, A., & Pea, R. (2024) · npj Mental Health Research · doi:10.1038/s44184-023-00047-6 · Cited by 250
Metadata
- Authors
- Clark, L., Pantidi, N., Cooney, O., Doyle, P., Garaialde, D., Edwards, J., Spillane, B., Gilmartin, E., Murad, C., Munteanu, C., Wade, V., & Cowan, B. R.
- Affiliations
- University College Dublin (IE)
- University College Cork (IE)
- Voysis (Ireland) (IE)
- Trinity College Dublin (IE)
- University of Toronto (CA)
- ORCID
- Venue
- Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2019-05-02
- Pages
- 1-12
- OpenAlex
- W4288359812
- Cited by
- 461
- References
- 50
- Citations by year
- 2026: 102 · 2025: 56 · 2024: 54 · 2023: 65 · 2022: 84 · 2021: 53 · 2020: 39 · 2019: 8
- FWCI
- 75.91
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Funders
- Irish Research Council (R17339)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Keywords
- chatbots, human-agent interaction, conversation quality, trust, bonds, common ground, context awareness, relationship stages, conversational agent design
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.
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.