Conceptual Metaphors Impact Perceptions of Human-AI Collaboration
Open accessThe DOI matches its Crossref record; 82 of the 82 references it cites were found in a registry or an index.
Abstract
With the emergence of conversational artificial intelligence (AI) agents, it is important to understand the mechanisms that influence users' experiences of these agents. In this paper, we study one of the most common tools in the designer's toolkit: conceptual metaphors. Metaphors can present an agent as akin to a wry teenager, a toddler, or an experienced butler. How might a choice of metaphor influence our experience of the AI agent? Sampling a set of metaphors along the dimensions of warmth and competence---defined by psychological theories as the primary axes of variation for human social perception---we perform a study $(N=260)$ where we manipulate the metaphor, but not the behavior, of a Wizard-of-Oz conversational agent. Following the experience, participants are surveyed about their intention to use the agent, their desire to cooperate with the agent, and the agent's usability. Contrary to the current tendency of designers to use high competence metaphors to describe AI products, we find that metaphors that signal low competence lead to better evaluations of the agent than metaphors that signal high competence. This effect persists despite both high and low competence agents featuring identical, human-level performance and the wizards being blind to condition. A second study confirms that intention to adopt decreases rapidly as competence projected by the metaphor increases. In a third study, we assess effects of metaphor choices on potential users' desire to try out the system and find that users are drawn to systems that project higher competence and warmth. These results suggest that projecting competence may help attract new users, but those users may discard the agent unless it can quickly correct with a lower competence metaphor. We close with a retrospective analysis that finds similar patterns between metaphors and user attitudes towards past conversational agents such as Xiaoice, Replika, Woebot, Mitsuku, and Tay.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“This comparative research has shown that interface metaphors, whether explicitly assigned by designers or implicitly adopted by users, significantly influence users' perceptions and interactions with AI systems.”
From Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems (2026) · cites this paper as [32]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Moreover, research shows that CUIs designed using human metaphors set high expectations as users perceive them to be more competent, but with subsequent use, these highly competent metaphors are rejected for metaphors that project less competence [39].”
From Examining Humanness as a Metaphor to Design Voice User Interfaces (2024) · cites this paper as [39]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“For example, Khadpe et al. [32] explored agentic metaphors that portrayed chatbots as different human personas and found that they changed user satisfaction with a system even when the system's capabilities were unchanged.”
From Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems (2026) · cites this paper as [32]
The cited source says what the claim attributes to it.
In the citing paper
“Comparative research on metaphors for AI has demonstrated the impact metaphors can have on user interactions with task-based AI systems, e.g., AI that assists with well-defined tasks such as travel planning [32] or waste sorting [46].”
From Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems (2026) · cites this paper as [32]
The cited source says what the claim attributes to it.
In the citing paper
“They found that the choice of metaphor had an impact on users’ pre-use as well as post-use perceptions.”
From Examining Humanness as a Metaphor to Design Voice User Interfaces (2024) · cites this paper as [39]
5 more claims about this paper
Create a free account to see every claim other papers make about this one.
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
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
Fiske, S. T., Cuddy, A. J. C., Glick, P., & Xu, J. (2002) · Journal of Personality and Social Psychology · doi:10.1037/0022-3514.82.6.878 · Cited by 7,364
(1997) · Choice Reviews Online · doi:10.5860/choice.34-3702 · Cited by 4,887
The Psychology of Everyday Things
Massaro, D. W., & Norman, D. A. (1990) · The American Journal of Psychology · doi:10.2307/1423268 · Cited by 3,466 · cited 1×
“In HCI, experiences of a system are typically understood as being mediated by a person’s mental model of that system [54].”
BackgroundForming impressions of personality.
Asch, S. E. (1946) · The Journal of Abnormal and Social Psychology · doi:10.1037/h0055756 · Cited by 2,508 · cited 1×
“These two dimensions have proven to far outweigh others and repeatedly come up as prime factors in literature [3, 38, 77].”
BackgroundCuddy, A. J. C., Fiske, S. T., & Glick, P. (2008) · Advances in Experimental Social Psychology · doi:10.1016/s0065-2601(07)00002-0 · Cited by 2,438 · cited 3×
“if the interaction with the agent is identical in both cases. In this paper, we test the effect of metaphors on evaluations of AI agents. We draw on the Stereotype Content Model (SCM) from psychology [16, 24], which demonstrates that the two dimensionsofwarmthandcompetencearetheprincipalaxesofhumansocialperception.Jud…”
BackgroundMethodInfluentialLinguistic Inquiry and Word Count (LIWC): Pronounced “Luke,” . . . and Other Useful Facts
Chung, C. K., & Pennebaker, J. W. (2012) · Applied Natural Language Processing · doi:10.4018/978-1-60960-741-8.ch012 · Cited by 2,151
The psychology of everyday things
Weld, D. S. (1989) · Artificial Intelligence · doi:10.1016/0004-3702(89)90083-0 · Cited by 2,105
FORMING IMPRESSIONS OF PERSONALITY
Asch, S. E. (1961) · Documents of Gestalt Psychology · doi:10.1525/9780520313514-018 · Cited by 2,081
Ferrara, E., Varol, O., Davis, C., Menczer, F., & Flammini, A. (2016) · Communications of the ACM · doi:10.1145/2818717 · Cited by 1,973
Research works printed but not linked: 12
- [11] Elaine Chang and Vishwac Kannan. 2018. Conversational AI: Best practices for building bots. https://medius.studios. ms/Embed/Video/BRK3225 -
- [12] Ana Paula Chaves and Marco Aurélio Gerosa. 2019. How should my chatbot interact? A survey on human-chatbot interaction design. CoRR abs/1904.02743 (2019). arXiv:1904.02743 http://arxiv.org/abs/1904.02743 - · arXiv
- [31] Jan Hartmann, Antonella De Angeli, and Alistair Sutcliffe. 2008. Framing the user experience: information biases on website quality judgement. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems . ACM, 855-864. -
- [39] Ralph Kimball and B Verplank E Harslem. 1982. Designing the Star user interface. Byte 7, 1982 (1982), 242-282. -
- [45] George Lakoff and Mark Johnson. 2008. Metaphors we live by . University of Chicago press. -
- [48] Q Vera Liao, Mas-ud Hussain, Praveen Chandar, Matthew Davis, Yasaman Khazaeni, Marco Patricio Crasso, Dakuo Wang, Michael Muller, N Sadat Shami, Werner Geyer, et al. 2018. All Work and No Play? Conversations with a question-and-answer chatbot in the wild. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems . ACM, 3. -
- 10.1111/0022--4537.00128 · doi:10.1111/0022--4537.00128
- [55] AE Nutt. 2017. The Woebot will see you now. the rise of chatbot therapy: Washington Post (2017). -
- [57] James W Pennebaker, Martha E Francis, and Roger J Booth. 2001. Linguistic inquiry and word count: LIWC 2001. Mahway: Lawrence Erlbaum Associates 71, 2001 (2001), 2001. -
- [62] C. Sandvig. 2015. Seeing the Sort: The Aesthetic and Industrial Defense of âĂIJThe Algorithm.âĂİ. Journal of the New Media Caucus, 11, 35-51 (2015). -
- [64] Robin Sease. 2008. MetaphorâĂŹs role in the information behavior of humans interacting with computers. Information technology and libraries 27, 4 (2008), 9-16. -
- [74] Peter Wallis and Emma Norling. 2005. The Trouble with Chatbots: social skills in a social world. Virtual Social Agents 29 (2005). -
Cited by
Items 201–228 of 228
Lost in Translation: Artificial Intelligence and the Burden of Bad Metaphors
Kūlis, M. (2026) · Synthese Library/Synthese library · doi:10.1007/978-3-032-10073-3_17
Diachronic Changes in the Framing of Metaphors: A Corpus-Based Study of IMF Economic Discourse
Jaradat, M. M., Talafha, D. K., & Younes, Z. B. B. (2026) · World Journal of English Language · doi:10.5430/wjel.v16n5p208
Hung, P.-K., Huang, Y., Liang, R., & Wensveen, S. S. A. G. (2026) · Designing Interactive Systems Conference · doi:10.1145/3800645.3812879
“In design practice, metaphors can both constrain and open technical possibilities [20, 79], provoke critical questioning [40, 92], and shape end-user perceptions of technologies and interactions [27, 69].”
Särestöniemi, M., Singh, D., Jarva, E., & Reponen, J. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-28819-6
AI as Arbiter? The Role of Artificial Intelligence in Cyberbullying Report Review Process
Lee, S., Kim, W., & Moon, W.-K. (2026) · Cyberpsychology Behavior and Social Networking · doi:10.1177/21522715261460961
“27,28 Extending these con fl icting fi ndings, the current study raises the following research question: RQ1: Would individuals prefer a human – AI collaboration-driven report review system over a solely human-or AI-driven report review system?”
Dudziak, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7008244
Constructing the Human-AI Boundary with Metaphors - A Demystification-Legitimation Paradox
Washik, M., & Heathcote-Fumador, I. E. (2026) · International Conference on Human Centric Artificial Intelligence (ICHCAI) · doi:10.1109/ichcai70183.2026.11607677
“Across studies, AI metaphors cluster into recurring themes: tools and artefacts, colleagues and teammates, apprentices and novices, experts and authorities, and threats and predators, each associated with a different way of positioning AI relative to human actors [28].”
Teixeira, M. C., Aebli, A., Klein, S. H., & Tschopp, M. V. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-26717-7_10
Analogies and Metaphors for Agentic AI: How Industry Practitioners Explain Emerging AI Systems
Stundzig, F., Heimburg, V., & Wiesche, M. (2026) · Mensch und Computer (MuC) · doi:10.1145/3820253.3820283
“However, while prior work has examined how users interpret metaphors in interaction contexts [17, 33], little is known about how industry practitioners themselves analogically and metaphorically conceptualize agentic AI systems at the moment of their emergence.”
InfluentialDull, dirty, and dangerous facets of human-AI collaboration for psychotherapy
Swinger, N., Baseman, C. M., & Arriaga, R. I. (2026) · Frontiers in Human Dynamics · doi:10.3389/fhumd.2026.1931983
AI as the New Paint: A Systematic Review of AI as a Design Material
Zhou, K., Koch, J., & Casiez, G. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3829807.3829862
The House with a Million Windows: Interactive Fiction for Narrative RestoryingPreprint
Kommers, C., Immel, S., Hemment, D., & Lee, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.12537
“Metaphors for AI, like ‘chat-bot,’ ‘assistant,’ or even ‘artificial intelligence’ itself, reveal some qualities of the technology while obscuring others and can strongly shape a user’s perception of the system [32].”
Ownership in AI-Assisted Everyday TasksPreprint
Wei, M., Subbiah, M., Lee, A., Dahmani, A., Edwards, D., Edwards, H., & Pavlick, E. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.20658
“) [Khadpe et al., 2020], which does not threaten ownership [Maier et al., 2026].”
Duan, W., Zhang, R., Weng, N., Freeman, G., & McNeese, N. J. (2026) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3816906
“Metaphors used to describe the AI (e.g., ”trained professional” vs. ”fresh graduate”) further induce different communication expectations [109].”
Rahman, M. H., Sadek, M., & Desai, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.25586
“…metaphor introducing an LLM as a collaborator versus a tool changes how people evaluate and use it, even when its behavior is held constant [28–30, 65 ], self-confidence follows it [76], and systems that extend users’ reasoning without a verdict behave differently from those that recommend one…”
Li, Y., Lallemand, C., & Bernhaupt, R. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3829807.3829813
Zhang, O. X., Shumsky, I., Hancock, J. T., Choudhury, M. D., & Liu, X. (2026) · doi:10.2196/preprints.110259
Self-citationAddison, I. P. (2025) · Library, Museums and Press - UDSpace (University of Delaware)
Porwol, P., Peters, T. M., & Scharlau, I. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101351
Designing metaphor-fluid voice user interfaces
Desai, S. (2024) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 2
Seeing us through machines: designing and building conversational AI to understand humans
Xiao, Z. (2023) · Illinois Digital Environment for Access to Learning and Scholarship (University of Illinois at Urbana-Champaign) · Cited by 3
Metaphor - one way of expressing implicit meaningPreprint
Kazakhbayeva, A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7606521
Heßler, P. O., Blay, T., Pfeiffer, J., & Hafenbrädl, S. (n.d.) · AIS Electronic Library (AISeL)
Xu, H., Liang, S., & Cheng, Q. (2026) · Information Technology and People · doi:10.1108/itp-05-2026-0970
Exploring How Warmth and Competence Shape Trust in Medical Voice Agents with Blind Users
Zhang, W., Xiao, Y., Yu, H., Feng, Y., Yin, D., & Qiao, J. (2026) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3797867.3828981
“A large body of research has shown that warmth and competence play a dominant role in explaining social judgments, affecting approach or avoidance tendencies and interpretations of others’ motives and behaviors [26, 38, 67].”
InfluentialFrom Bias to Positionality: A critical grammar for Large Language ModelsPreprint
Murray-Rust, D., Giaccardi, E., Bomba, F., & Lupetti, M. L. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.14079
Heßler, P., Blay, T., Pfeiffer, J., & Hafenbrädl, S. (2026) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5445/ir/1000199060
Where Do I 'Add the Egg'?: Exploring Agency and Ownership in AI Creative Co-Writing Systems
Carrera, D., Thomas-Mitchell, J., & Wigdor, D. (2025) · arXiv · doi:10.48550/arxiv.2509.15440
“Comparative research on metaphors for AI has demonstrated the impact metaphors can have on user interactions with task-based AI systems, e.g., AI that assists with well-defined tasks such as travel planning [36] or waste sorting [52].”
Metadata
- Authors
- Khadpe, P., Krishna, R., Fei-Fei, L., Hancock, J. T., & Bernstein, M. S.
- Affiliations
- Stanford University (US)
- Venue
- Proceedings of the ACM on Human-Computer Interaction
- Published
- 2020-10-14
- Volume
- 4
- Issue
- CSCW2
- Pages
- 1-26
- ISSN
- 2573-0142 (ISSN-L)
- OpenAlex
- W3047508744
- Cited by
- 183
- References
- 79
- Citations by year
- 2026: 53 · 2025: 40 · 2024: 34 · 2023: 29 · 2022: 18 · 2021: 7 · 2020: 2
- FWCI
- 15.30
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings of the ACM on Human-Computer Interaction (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Brown Institute for Media Innovation
- Toyota Research Institute
- 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 › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- conceptual metaphor, human-AI collaboration, conversational AI agents, warmth and competence, intention to use, perceived usability, user attitudes toward AI, AI 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.