Hey Google, Do You Have a Personality? Designing Personality and Personas for Conversational Agents
The DOI matches its Crossref record; 24 of the 25 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
Conversational agents designed to interact through natural language are often imbued with human-like personalities. At times, the agent might also have a distinct persona with traits such as gender, age, or a backstory. Designing such personality or persona for conversational agents has become a common design practice. In this work, we review the emerging literature on designing agent persona or personality, and reflect on these approaches, along with the personas that are created for common conversational agents. We discuss open questions with regards to three aspects: meeting user needs, the ethics of deception, and reinforcing social stereotypes through conversational agents. We hope this work can provoke researchers and practitioners to critically reflect on their approach for designing personality or persona of conversational agents.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“emphasized that crafting female personas in subordinate roles can perpetuate existing societal biases.”
From Examining Humanness as a Metaphor to Design Voice User Interfaces (2024) · cites this paper as [63]
In the citing paper
“highlighting how the default voices of commercial VUIs often resemble “white women from the West””
From Examining Humanness as a Metaphor to Design Voice User Interfaces (2024) · cites this paper as [63]
In the citing paper
“The ethical concerns regarding the deployment of metaphor-based stereotype-reinforcing voice user interfaces have been extensively documented [19,36,45].”
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 [45]
Citations
Cites
On seeing human: A three-factor theory of anthropomorphism
Epley, N., Waytz, A., & Cacioppo, J. T. (2007) · Psychological Review · doi:10.1037/0033-295x.114.4.864 · Cited by 4,069 · cited 1×
“, ascribe human-like properties, characteristics, or mental states to nonhuman agents [8]) and perceive them as human-like to even associate social roles of friend or a partner with the agent [19, 22, 23].”
BackgroundConversational 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 1×
“Conversational agents have long been used in healthcare [16], e-learning [14] or for social companionship purposes [29].”
BackgroundGranny and the robots: ethical issues in robot care for the elderly
Sharkey, A., & Sharkey, N. (2012) · Ethics and Information Technology · doi:10.1007/s10676-010-9234-6 · Cited by 985 · cited 1×
“Researchers working on Human-Robot Interaction have already cautioned us of the underlying concerns of such de-ception (including misplaced trust, replacing human care) [27, 28], and is something we should not be sidelining as we design the next generation of conversational agents.”
BackgroundThe design and implementation of Xiaoice, an empathetic social chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2020) · Computational Linguistics · doi:10.1162/coli_a_00368 · Cited by 777 · cited 3×
“Despite being extremely knowledgeable due to her access to large amounts of data and knowledge, XiaoIce never comes across as egotistical and only demonstrates her wit and creativity when appropriate [33].”
BackgroundMethodThe Design and Implementation of XiaoIce, an Empathetic Social Chatbot
Zhou, L., Gao, J., Li, D., & Shum, H.-Y. (2018) · arXiv · doi:10.48550/arxiv.1812.08989 · Cited by 777 · cited 3×
“Despite being extremely knowledgeable due to her access to large amounts of data and knowledge, XiaoIce never comes across as egotistical and only demonstrates her wit and creativity when appropriate [33].”
BackgroundMethod"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 · cited 1×
“, ascribe human-like properties, characteristics, or mental states to nonhuman agents [8]) and perceive them as human-like to even associate social roles of friend or a partner with the agent [19, 22, 23].”
BackgroundOgbonnaya-Ogburu, I. F., Smith, A. D. R., To, A., & Toyama, K. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376392 · Cited by 396 · cited 1×
“While not having these traits makes sense in a way, since it is not a living thing to have such qualities, but what does it mean to design a fictional human-like character that does not have a race or belong to a particular region? Looking at this through the lens of racial blindness perpetuated through technology (wh…”
Background"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 2×
“For example, one study found that the human-like qualities of the agent affect how users might act towards the agent, where some users did not want to hurt the agent’s feelings [3].”
BackgroundI'd blush if I could: closing gender divides in digital skills through education
UNESCO, & Coalition, E. S. (2019) · doi:10.54675/rapc9356 · Cited by 262 · cited 2×
“Google Assistant used to work as a personal assistant to a very popular late night TV satirical pundit and enjoys kayaking [12, 30].”
BackgroundMethodPradhan, A., Findlater, L., & Lazar, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359316 · Cited by 223 · cited 1×
“, ascribe human-like properties, characteristics, or mental states to nonhuman agents [8]) and perceive them as human-like to even associate social roles of friend or a partner with the agent [19, 22, 23].”
BackgroundSelf-citationAsking more of Siri and Alexa: feminine persona in service of surveillance capitalism
Woods, H. S. (2018) · Critical Studies in Media Communication · doi:10.1080/15295036.2018.1488082 · Cited by 222 · cited 2×
“Will this reinforce negative gender stereotypes and also marginalize non-binary individuals, as some researchers begin to argue [4, 20, 30, 32]?”
BackgroundPersonas: from theory to practices
Chang, Y.-N., Lim, Y.-K., & Stolterman, E. (2008) · Proceedings of the 5th Nordic conference on Human-computer interaction: building bridges · doi:10.1145/1463160.1463214 · Cited by 203 · cited 2×
“They also consider the persona of the user (a fictional identity construct of the user representing some characteristics of the user along with their needs and goals [2]) and map the personality of the agent to the user persona.”
BackgroundWe need to talk about deception in social robotics!
Sharkey, A., & Sharkey, N. (2021) · Ethics and Information Technology · doi:10.1007/s10676-020-09573-9 · Cited by 179 · cited 1×
“an agent? By designing more human-like agents are we tricking users in some way or persuading them to do something they would not otherwise? Researchers working on Human-Robot Interaction have already cautioned us of the underlying concerns of such deception (including misplaced trust, replacing human care) [27, 28],”
BackgroundPersonification of the Amazon Alexa: BFF or a Mindless Companion
Lopatovska, I., & Williams, H. (2018) · Proceedings of the 2018 Conference on Human Information Interaction&Retrieval - CHIIR '18 · doi:10.1145/3176349.3176868 · Cited by 160 · cited 2×
“, ascribe human-like properties, characteristics, or mental states to nonhuman agents [8]) and perceive them as human-like to even associate social roles of friend or a partner with the agent [19, 22, 23].”
BackgroundIntimate Futures: Staying with the Trouble of Digital Personal Assistants through Design Fiction
Søndergaard, M. L. J., & Hansen, L. K. (2018) · Proceedings of the 2018 Designing Interactive Systems Conference · doi:10.1145/3196709.3196766 · Cited by 128 · cited 1×
“But what happens when this agent is female and is portrayed as submissive and docile? Will this reinforce negative gender stereotypes and also marginalize non-binary individuals, as some researchers begin to argue [4, 20, 30, 32]? We argue that examining the persona that designers create – which play a key role in det…”
BackgroundConversational Agents in E-Learning
Kerry, A., Ellis, R., & Bull, S. (2009) · Springer eBooks · doi:10.1007/978-1-84882-215-3_13 · Cited by 113 · cited 1×
“Conversational agents have long been used in healthcare [16], e-learning [14] or for social companionship purposes [29].”
BackgroundThe effect of voice and humour on users’ perceptions of personal intelligent agents
Moussawi, S., & Benbunan-Fich, R. (2021) · Behaviour & Information Technology · doi:10.1080/0144929x.2020.1772368 · Cited by 83 · cited 1×
“Some research argues that having a distinct persona or personality can contribute a cohesive and consistence presence of the conversational agent for users [17] and increase trust and the intention to use the technology [21].”
BackgroundVölkel, S. T., Schödel, R., Buschek, D., Stachl, C., Winterhalter, V., Bühner, M., & Hussmann, H. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376210 · Cited by 65 · cited 1×
“…for human personality does not adequately describe agent personality and they propose a personality model with alternative dimensions (confrontational, dysfunctional, serviceable, unstable, approachable, social-entertaining, social-inclined, social-assisting, self-conscious, and artificial) [31].”
BackgroundVölkel, S. T., Schödel, R., Buschek, D., Stachl, C., Winterhalter, V., Bühner, M., & Hußmann, H. (2020) · Alexandria (UniSG) (University of St.Gallen) · Cited by 55
Eschewing Gender Stereotypes in Voice Assistants to Promote Inclusion
Danielescu, A. (2020) · Proceedings of the 2nd Conference on Conversational User Interfaces · doi:10.1145/3405755.3406151 · Cited by 48 · cited 2×
“Will this reinforce negative gender stereotypes and also marginalize non-binary individuals, as some researchers begin to argue [4, 20, 30, 32]?”
BackgroundRacial mirroring effects on human-agent interaction in psychotherapeutic conversations
Liao, Y., & He, J. (2020) · Proceedings of the 25th International Conference on Intelligent User Interfaces · doi:10.1145/3377325.3377488 · Cited by 43 · cited 4×
“Even though some emerging work shows racial preferences might not disappear in human-agent interaction [18], we still continue to follow a race blind approach to designing conversational agents.”
BackgroundInfluentialInteraction Strategies for an Affective Conversational Agent
Smith, C., Crook, N., Charlton, D., Boye, J., de la Camara, R. S., Turunen, M., Benyon, D., Gambäck, B., Mival, O., Webb, N., et al. (2011) · Presence: Teleoperators and Virtual Environments · doi:10.1162/pres_a_00063 · Cited by 39 · cited 1×
“Conversational agents have long been used in healthcare [16], e-learning [14] or for social companionship purposes [29].”
BackgroundDesigning Personalities of Conversational Agents
Kim, H., Koh, D. Y., Lee, G., Park, J., & Lim, Y.-K. (2019) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3290607.3312887 · Cited by 35 · cited 5×
“For example, some sources mention that Alexa is designed to be “smart, approachable, humble, enthusiastic, helpful and friendly” [5, 15, 25] or Siri is designed to be “friendly and humble – but also with an edge” [1, 24, 34].”
BackgroundInfluentialA Bot is Not a Polyglot: Designing Personalities for Multi-Lingual Conversational Agents
Danielescu, A., & Christian, G. (2018) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3170427.3174366 · Cited by 31 · cited 2×
“For example, some sources mention that Alexa is designed to be “smart, approachable, humble, enthusiastic, helpful and friendly” [5, 15, 25] or Siri is designed to be “friendly and humble – but”
BackgroundDo I have a say? Using conversational agents to re-imagine human-machine autonomy
Sankaran, S., Zhang, C., Funk, M., Aarts, H., & Markopoulos, P. (2020) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3405755.3406135 · Cited by 23
Research works printed but not linked: 8
- Arnold Kim. 2011. How Apple Approached Developing Siri's Personality. MacRumors. Retrieved April 6, 2021 from https://www.macrumors.com/2011/10/15/how-apple-approached-developing-siris-personality/
- Stephan Diederich, Alfred Brendel, and Lutz Kolbe. 2019. Towards a Taxonomy of Platforms for Conversational Agent Design. Wirtschaftsinformatik 2019 Proceedings. Retrieved from https://aisel.aisnet.org/wi2019/track10/papers/1
- Philip R. Doyle, Justin Edwards, Odile Dumbleton, Leigh Clark, and Benjamin R. Cowan. 2019. Mapping Perceptions of Humanness in Intelligent Personal Assistant Interaction. In Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services (MobileHCI ’19), 1–12. https://doi.org/10.1145/3338286.3340116 · DOI · Paper page
- Catia M Ferreira and Sviatlana Hoehn. Crafting Conversational Agents’ Personality in a User-centric Context. In Proceedings of the 31st Benelux Conference on Artificial Intelligence (BNAIC 2019) and the 28th Belgian Dutch Conference on Machine Learning (Benelearn 2019), 2.
- Google. Create a persona - Conversation design process - Conversation design. Retrieved April 2, 2019 from https://designguidelines.withgoogle.com/conversation/conversation-design-process/create-a-persona.html#create-a-persona-how-do-i-create-one
- N. Lessio and A. Morris. 2020. Toward Design Archetypes for Conversational Agent Personality. In 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 3221–3228. https://doi.org/10.1109/SMC42975.2020.9283254 · DOI
- Janko Roettgers. 2019. How Alexa Got Her Personality. Variety. Retrieved July 28, 2020 from https://variety.com/2019/digital/news/alexa-personality-amazon-echo-1203236019/
- 2011. Apple gave Siri AI personal assistant its edge. MacDailyNews. Retrieved April 6, 2021 from https://macdailynews.com/2011/10/16/apple-gave-siri-ai-personal-assistant-its-edge/
Cited by
Janson, A. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2023.107954 · Cited by 187
“…appearance (San-non et al., 2018), induce social presence perceptions related to chatbots for the following reasons: Individuals feel the need to attribute a personality to chatbots, even when little information is available (Pradhan & Lazar, 2021; Purington et al., 2017; Tolzin & Janson, 2023).”
BackgroundHa, 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 135
BIG5-CHAT: Shaping LLM Personalities Through Training on Human-Grounded Data
Li, W., Liu, J., Liu, A. W., Zhou, X., Diab, M., & Sap, M. (2025) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2025.acl-long.999 · Cited by 118
A Systematic Review of Ethical Concerns with Voice Assistants
Seymour, W., Zhan, X., Coté, M., & Such, J. M. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604679 · Cited by 68
Sun, G., Zhan, X., & Such, J. (2024) · ACM Conversational User Interfaces 2024 · doi:10.1145/3640794.3665887 · Cited by 55
Metadata
- Authors
- Pradhan, A., & Lazar, A.
- Affiliations
- University of Maryland, College Park (US)
- Venue
- Proceedings of the 3rd Conference on Conversational User Interfaces
- Publisher
- ACM
- Published
- 2021-07-27
- Pages
- 1-4
- OpenAlex
- W3186985373
- Cited by
- 50
- References
- 24
- Citations by year
- 2026: 7 · 2025: 18 · 2024: 10 · 2023: 8 · 2022: 7
- FWCI
- 10.66
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM Conference on Conversational User Interfaces (CUI) (publishedVersion)
- Funders
- National Science Foundation (IIS-1816145)
- Topics
- Social Sciences › Psychology › Social Psychology › Social Robot Interaction and HRI
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- chatbots, agent personality, personas, natural language interaction, ethics of deception, social stereotypes, user needs, human-AI interaction
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.