Examining Humanness as a Metaphor to Design Voice User Interfaces
Open accessThe DOI matches its Crossref record; 77 of the 79 references it cites were found in a registry or an index, and 2 are not checked yet; 8 of the 58 sources its claims cite were checked for support.
Abstract
Voice User Interfaces (VUIs) increasingly leverage ‘humanness’ as a foundational design metaphor, adopting roles like ‘assistants,’ ‘teachers,’ and ‘secretaries’ to foster natural interactions. Yet, this approach can sometimes misalign user trust and reinforce societal stereotypes, leading to socio-technical challenges that might impede long-term engagement. This paper explores an alternative approach to navigate these challenges—incorporating non-human metaphors in VUI design. We report on a study with 240 participants examining the effects of human versus non-human metaphors on user perceptions within health and finance domains. Results indicate a preference for the human metaphor (doctor) over the non-human (health encyclopedia) in health contexts for its perceived enjoyability and likeability. In finance, however, user perceptions do not significantly differ between human (financial advisor) and non-human (calculator) metaphors. Importantly, our research reveals that the explicit awareness of a metaphor’s use influences adoption intentions, with a marked preference for non-human metaphors when their metaphorical nature is not disclosed. These findings highlight context-specific conversation design strategies required in integrating non-human metaphors into VUI design, suggesting tradeoffs and design considerations that could enhance user engagement and adoption.
Verified 2026-10-05 · 2 references not checked yet
Overview
CoChat Summary
TL;DR
In a 2x4 mixed-subjects study with 240 frequent VUI users, human metaphors (doctor, financial advisor) were compared with non-human metaphors (health encyclopedia, calculator) in health and finance. Human metaphors were more enjoyable and likeable in health and more trusted overall, but finance showed no significant metaphor differences; awareness of a non-human metaphor affected adoption intentions.
Key findings
- In health, the human metaphor (doctor) led to higher perceived enjoyment than the non-human metaphor (health encyclopedia), F(1, 238) = 4.663, p = .032, η²p = 0.019, and higher likeability, F(1, 238) = 7.551, p = .006, η²p = 0.031. Means: enjoyment 5.43 ± 1.12 vs. 5.32 ± 1.24; likeability 4.32 ± 0.61 vs. 4.22 ± 0.69.
- In finance, user perceptions did not significantly differ between the human metaphor (financial advisor) and non-human metaphor (calculator) for enjoyment, likeability, trust, intelligence, or intention to adopt (e.g., enjoyment interaction p = .832; likeability p = .325; trust p = .659; intelligence p = .325; intention p = .262).
- Overall, participants trusted human metaphors more than non-human metaphors, F(1, 238) = 5.577, p = .019, η²p = 0.023; overall enjoyment also favored human metaphors, F(1, 238) = 9.798, p = .002, η²p = 0.040, as did overall likeability, F(1, 238) = 8.913, p = .003, η²p = 0.036.
- There was no significant overall main effect of metaphor type on intention to adopt, F(1, 238) = 1.193, p = .276, η²p = 0.005, but a significant interaction involving awareness and non-human metaphors emerged, F(1, 238) = 4.116, p = .044, η²p = 0.017, with a marked preference for non-human metaphors when their metaphorical nature was not disclosed. Perceived intelligence did not differ by metaphor across domains, overall F(1, 238) = 0.447, p = .504, η²p = 0.002.
Methods
- The study used a 2x4 factorial design: awareness level (explicit vs. implicit) was between-subjects, and metaphor type was within-subjects with four levels—doctor and health encyclopedia in health, financial advisor and calculator in finance. Participants experienced all four metaphor types within their assigned awareness condition, with presentation order counterbalanced.
- Participants were 240 Prolific users (M = 43.21, SD = 13.73), all U.S.-based, highly proficient English speakers with prior VUI experience; 82.5% reported being very or extremely familiar with VUIs, and 58.3% used them daily. Audio clips were generated with Speechify TTS, using a female-sounding voice for VUI “Z” and a male-sounding voice for the user.
- Measures included perceived enjoyment, intention to adopt, trust, likeability, and intelligence, plus optional qualitative feedback. Main analysis used repeated measures ANOVA with metaphor type as the within-subjects variable and awareness as the between-subjects factor.
Limitations
- The paper states that participants formed impressions from hypothetical dialogues rather than direct interaction, making findings observational rather than experiential; it also notes that VUI perceptions and user relationships change over time, so longitudinal research is needed.
- The paper states that the study was restricted to native English speakers living in the U.S. because metaphor use depends on cultural factors, limiting generalizability across cultures.
- Evident from the text: the qualitative thematic analysis was conducted by the first author alone, and the study used scripted six-turn dialogues with synthetic TTS voices, which may not capture real-world VUI interaction dynamics.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
8 Valid · 2 Not valid · 39 Not checked · 52 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“They found that the choice of metaphor had an impact on users’ pre-use as well as post-use perceptions.”
What the sources say
- Supportedcites [39] source
Study 1 (p. 9) frames the experiment as examining "the effects of metaphors attached to the conversational system on user pre-use expectations and post-use evaluations," and its results sections report significant metaphor effects on pre-use usability/warmth (§4.5, pp. 11-12) and on post-use usability/warmth (§4.6, p. 12). The Conclusion (p. 22) states directly that "these conceptual metaphors change users' pre-use expectations as well as their post-use evaluations of the system." The only mild shift is terminology: the source's agent was a Wizard-of-Oz conversational agent rather than a deployed chatbot, but the attributed finding is fully supported. (LLM, conf=0.93)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“This finding is also supported by Pradhan et al. [62], who found older adults ontologically cat-egorized VUIs as a person as well as an object (or something in between).”
What the sources say
- Supportedcites [62] source
Section 3.2 ('The Social Role of Alexa: Movement between Ontological Categories') reports Alexa was described as 'a person' by all participants (also 'a friend', 'a phantom friend') while the same people later called it a 'programmed' voice, machine or 'object' — directly supporting person-and-object categorization by older adults. Section 3.1.3 ('Neither human nor object') covers instances where perceptions 'did not clearly classify into "human-like" or "object-like"', resembling Kahn et al.'s in-between category, which supports the parenthetical. The Discussion (4.2) refines this by stressing fluid movement along a 'human-object' spectrum rather than a continuous in-between state, but does not contradict the claim as hedged. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“This miscalibration can result in infrequent use [16] or non-use [14].”
What the sources say
- Supportedcites [16] source
In 'The Limitations of Humanness as a Metaphor' our copy states directly that 'the mismatch between expectations and system performance may be affecting people's levels of IPA use', which is exactly the possibility the citing sentence attributes to this source for infrequent use. The same section grounds it in the study: participants' behaviours 'are caused by a perceived mismatch between the system's capabilities and the user's model of how the system works', and the authors propose redesigning the interlocutor to 'manage user expectations'. The hedged 'may/can' framing matches. The 'non-use' half of the sentence is carried by a different citation ([14]) and is not at stake here. (LLM, conf=0.85)
- Not checked yetcites [14] source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In finance, however, user perceptions do not significantly differ between human (financial advisor) and non-human (calculator) metaphors.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“with a marked preference for non-human metaphors when their metaphorical nature is not disclosed.”
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
47 more claims
Create a free account to see all 101 claims and to verify the 50 references still open.
- Probably not a substantial claim. 37
- It may state two separate claims as one. 19
Statistics recomputed
Every reported test result, recomputed from its test statistic and degrees of freedom. A result shows as not adding up only once an independent check has confirmed it.
- ConsistentF(1, 238) = 4.663reported p = .032 · recomputed p = .032
“F(1, 238) = 4.663, p = .032”
- ConsistentF(1, 238) = 0.376reported p = .54 · recomputed p = .540
“F(1, 238) = 0.376, p = .540”
- ConsistentF(1, 238) = 0.045reported p = .832 · recomputed p = .832
“F(1, 238) = 0.045, p = .832”
- ConsistentF(1, 238) = 0.023reported p = .879 · recomputed p = .880
“F(1, 238) = 0.023, p = .879”
- ConsistentF(1, 238) = 9.798reported p = .002 · recomputed p = .002
“F(1, 238) = 9.798, p = .002”
23 more recomputed tests
Create a free account to see every test the Stats check recomputed.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Self-check results appear here once an independent check has confirmed them.
Citations
Cites
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 · cited 1×
“In most cases, the anthro-pomorphism in users originates from “overlearned social behaviors” [58].”
BackgroundBartneck, C., Kulić, D., Croft, E., & Zoghbi, S. (2009) · International Journal of Social Robotics · doi:10.1007/s12369-008-0001-3 · Cited by 3,193 · cited 1×
“You can also adjust the coverage amount based on your most critical financial needs to find a balance between sufficient coverage and affordability. two items on 7-point Likert scale: “If available, I intend to start using Z within the next month,” and “If available, in the next months, I plan to…”
BackgroundResistance to Medical Artificial Intelligence
Longoni, C., Bonezzi, A., & Morewedge, C. K. (2019) · Journal of Consumer Research · doi:10.1093/jcr/ucz013 · Cited by 2,015 · cited 1×
“The tone or delivery style of commercial VUIs does not change based on user request.”
BackgroundFoundations for an Empirically Determined Scale of Trust in Automated Systems
Jian, J.-Y., Bisantz, A. M., & Drury, C. G. (2000) · International Journal of Cognitive Ergonomics · doi:10.1207/s15327566ijce0401_04 · Cited by 1,799
Principles of Interactive Computer Graphics
Land, D., Newman, W. M., & Sproull, R. F. (1975) · Leonardo · doi:10.2307/1573035 · Cited by 1,562 · cited 1×
“GUIs rely on a primary ‘desktop’ metaphor, which has undergone numerous iterations to provide users with a mental model for navigating visual interfaces [59].”
MethodLuger, 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 1×
“These folk theories stem from the discrepancy between what the users expect based on the metaphors provided to them and the actual experience of using CUIs [48], also explained by the concept of Norman’s “gulf of execution” [60].”
BackgroundAraujo, T. (2018) · Computers in Human Behavior · doi:10.1016/j.chb.2018.03.051 · Cited by 1,156 · cited 1×
“Related studies similarly indicated that anthropomorphizing VUIs can increase their perceived social presence and, in turn, affects users’ propensity to trust them [3, 64].”
BackgroundPersonality, coping, and coping effectiveness in an adult sample
McCrae, R. R., & Costa, P. T. (1986) · Journal of Personality · doi:10.1111/j.1467-6494.1986.tb00401.x · Cited by 1,113 · cited 1×
“They found that users found metaphors that were similar to them (in terms of: openness, conscientiousness, extraversion, agreeableness, and neuroticism (OCEAN) [51]) were perceived to be more likable and trustworthy.”
BackgroundChatbots and Conversational Agents in Mental Health: A Review of the Psychiatric Landscape
Vaidyam, A. N., Wisniewski, H., Halamka, J. D., Kashavan, M. S., & Torous, J. B. (2019) · The Canadian Journal of Psychiatry · doi:10.1177/0706743719828977 · Cited by 1,048 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundBansal, G., Zahedi, F. “., & Gefen, D. (2010) · Decision Support Systems · doi:10.1016/j.dss.2010.01.010 · Cited by 958 · cited 1×
“Subject sensitivity and privacy concerns are important considerations that can affect users’ intention to disclose information regarding their health online [4].”
BackgroundQiu, L., & Benbasat, I. (2009) · Journal of Management Information Systems · doi:10.2753/mis0742-1222250405 · Cited by 737 · cited 1×
“Related studies similarly indicated that anthropomorphizing VUIs can increase their perceived social presence and, in turn, affects users’ propensity to trust them [3, 64].”
BackgroundVoice 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 1×
“Additionally, VUIs utilize a request-response mechanism that could be effective for executing command-oriented tasks but falls short of facilitating genuine ‘conversations’ [61] and thus fall significantly short of the human-human communication benchmark.”
BackgroundConversational Agents in Health Care: Scoping Review and Conceptual Analysis
Tudor Car, L., Dhinagaran, D. A., Kyaw, B. M., Kowatsch, T., Joty, S., Theng, Y.-L., & Atun, R. (2020) · Journal of Medical Internet Research · doi:10.2196/17158 · Cited by 553 · cited 1×
“Some most commonly used personalities in this sensitive setting are coach-like, healthcare-expert, professional-like, informal, etc. [74].”
BackgroundHow perceptions of intelligence and anthropomorphism affect adoption of personal intelligent agents
Moussawi, S., Koufaris, M., & Benbunan-Fich, R. (2021) · Electronic Markets · doi:10.1007/s12525-020-00411-w · Cited by 406 · cited 2×
“To assess perceived enjoyment , we employ Moussawi et al.’s adapted survey [57], comprising three items on a 7-point Likert scale: “While using Z, I would find the interaction enjoyable,” “While using Z, I would find this interaction interesting,” and “While using Z, I would find the interaction…”
MethodMiner, A. S., Milstein, A., Schueller, S., Hegde, R., Mangurian, C., & Linos, E. (2016) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2016.0400 · Cited by 368 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundMusic, Search, and IoT: How People (Really) Use Voice Assistants
Ammari, T., Kaye, J., Tsai, J. Y., & Bentley, F. (2019) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3311956 · Cited by 356
Metaphor Analysis: Research Practice in Applied Linguistics, Social Sciences and the Humanities
Cameron, L., & Maslen, R. W. (2010) · Cited by 353
"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 3×
“This miscalibration can result in infrequent use [16] or non-use [14].”
BackgroundInfluential"Hey Alexa, What's Up?": A Mixed-Methods Studies of In-Home Conversational Agent Usage
Sciuto, A., Saini, A., Forlizzi, J., & Hong, J. I. (2018) · Proceedings of the 2018 Designing Interactive Systems Conference · doi:10.1145/3196709.3196772 · Cited by 327 · cited 1×
“For health, we designed two metaphorical VUIs that acted as a ‘doctor’ or a ‘health encyclopedia.’”
MethodTaking the time to care: empowering low health literacy hospital patients with virtual nurse agents
Bickmore, T. W., Pfeifer, L. M., & Jack, B. W. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518891 · Cited by 289 · cited 1×
“For instance, conversational style choices such as using humor, providing personalized and timely feedback, or starting the conversation with a social chat have proven beneficial to enhancing the overall user experience [7].”
BackgroundIndurkhya, B. (1992) · Studies in Cognitive Systems · doi:10.1007/978-94-017-2252-0 · Cited by 254
The reification of metaphor as a design tool
Blackwell, A. F. (2006) · ACM Transactions on Computer-Human Interaction · doi:10.1145/1188816.1188820 · Cited by 253 · cited 1×
“…is complemented by various secondary metaphors (e.g., folders, files, bins) and auxiliary metaphors (e.g., scrolling, icons, logging) — we recommend Alan Blackwell’s article [8] for a comprehensive overview of the history of desk-top metaphor and the idea of using metaphor as a design tool.”
BackgroundDeVito, M. A., Birnholtz, J., Hancock, J. T., French, M., & Liu, S. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3173694 · Cited by 244 · cited 1×
“However, despite this, the users often form their own conceptual understandings of these systems through folk theories [25].”
BackgroundHildebrand, C., & Bergner, A. (2021) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-020-00753-z · Cited by 231 · cited 1×
“In the investing context, conversational robo-advisors are a popular use case [11, 19, 32, 54].”
BackgroundPradhan, A., Findlater, L., & Lazar, A. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359316 · Cited by 223 · cited 2×
“Moreover, users fluctuated between human and non-human metaphors seamlessly without cognitive dissonance.”
BackgroundAI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Wortman Vaughan, J. (2024) · Harvard Data Science Review · doi:10.1162/99608f92.8036d03b · Cited by 210
AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap
Liao, Q. V., & Vaughan, J. W. (2023) · arXiv · doi:10.48550/arxiv.2306.01941 · Cited by 209 · cited 1×
“We report on a study with 240 participants examining the effects of human versus non-human metaphors on user perceptions within health and finance domains.”
BackgroundMetaphor Analysis in Psychology—Method, Theory, and Fields of Application
Moser, K. S. (2000) · Forum Qualitative Sozialforschung / Forum: Qualitative Social Research · doi:10.17169/fqs-1.2.1090 · Cited by 206 · cited 2×
“This was done because the use of metaphors depends on cultural factors [55], which could introduce additional confounding variables to this study.”
BackgroundKim, S., & Choudhury, A. (2021) · Computers in Human Behavior · doi:10.1016/j.chb.2021.106914 · Cited by 200 · cited 1×
“Often, these folk theories are disseminated in the form of metaphors, including explanations for how CUIs work (e.g., “ it’s like a computer chip that has stuff on it ” [40] or “ genie in the bottle ” [43]) or making sense of conversational errors (e.g., “ like a silly child ” [23]).”
BackgroundConceptual 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 · cited 6×
“Of course, a humanness metaphor is also somewhat nuanced because it gives rise to questions like ‘What kind of human?,’ ‘doing what?’”
BackgroundResultInfluentialAt Your Service: Designing Voice Assistant Personalities to Improve Automotive User Interfaces
Braun, M., Mainz, A., Chadowitz, R., Pfleging, B., & Alt, F. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300270 · Cited by 182 · cited 1×
“Researchers have also found relationships between the per-sonalities projected by the metaphors and the personalities of the end-users.”
BackgroundMetaphor and Cognition: An Interactionist Approach
Indurkhya, B. (1992) · Cited by 130
The elements of friendly software design
Heckel, P. (1984) · Medical Entomology and Zoology · Cited by 121
Ethical implications of conversational agents in global public health
Luxton, D. D. (2020) · Bulletin of the World Health Organization · doi:10.2471/blt.19.237636 · Cited by 108 · cited 1×
“This is particularly important given that VUIs are perceived as free from personal bias and induce less anxiety in patients when disclosing risky health behaviors [50].”
BackgroundColburn, T. R., & Shute, G. M. (2008) · Journal of Applied Logic · doi:10.1016/j.jal.2008.09.005 · Cited by 107 · cited 1×
“These metaphors are so ubiquitous in the language of computing that we have ceased to notice them [15], thereby becoming ‘dead’ metaphors [66].”
BackgroundThe Effect of Humanizing Robo‐Advisors on Investor Judgments*
Hodge, F. D., Mendoza, K. I., & Sinha, R. K. (2020) · Contemporary Accounting Research · doi:10.1111/1911-3846.12641 · Cited by 103
Godspeed Questionnaire Series: Translations and Usage
Bartneck, C. (2023) · International Handbook of Behavioral Health Assessment · doi:10.1007/978-3-030-89738-3_24-1 · Cited by 100
Understanding Affective Experiences with Conversational Agents
Yang, X., Aurisicchio, M., & Baxter, W. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300772 · Cited by 95 · cited 1×
“Within VUI literature, there is significant interest beyond mere usability, exploring how VUIs can contribute to user enjoyment [81] or enhance the quality of life [24].”
BackgroundJackendoff, R. S., & Aaron, D. H. (1991) · Language · doi:10.2307/415109 · Cited by 91
Once a Kind Friend is Now a Thing: Understanding How Conversational Agents at Home are Forgotten
Cho, M., Lee, S.-S., & Lee, K.-P. (2019) · Proceedings of the 2019 on Designing Interactive Systems Conference · doi:10.1145/3322276.3322332 · Cited by 90 · cited 4×
“Further, perceptions of VUIs, along with the users’ relationship with them, change over time [14].”
BackgroundInfluentialCheng, A., Raghavaraju, V., Kanugo, J., Handrianto, Y. P., & Shang, Y. (2018) · 2018 15th IEEE Annual Consumer Communications & Networking Conference (CCNC) · doi:10.1109/ccnc.2018.8319283 · Cited by 82 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundAssistive Conversational Agent for Health Coaching: A Validation Study
Fadhil, A., Wang, Y., & Reiterer, H. (2019) · Methods of Information in Medicine · doi:10.1055/s-0039-1688757 · Cited by 77 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundAlexa as Coach: Leveraging Smart Speakers to Build Social Agents that Reduce Public Speaking Anxiety
Wang, J., Yang, H., Shao, R., Abdullah, S., & Sundar, S. S. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376561 · Cited by 75 · cited 1×
“To this end, researchers and designers have deployed CUIs to fulfill various social roles, such as ‘teachers’ [20, 37], ‘coaches’ [21, 79], ‘storytellers’ [22], ‘brokers’ [45] or ‘therapists’ [56].”
Zhu, H., Pysander, E.-L. S., & Söderberg, I. (2023) · Data and Information Management · doi:10.1016/j.dim.2023.100041 · Cited by 74
One AI Does Not Fit All: A Cluster Analysis of the Laypeople’s Perception of AI Roles
Kim, T., Molina, M. D., Rheu, M. (., Zhan, E. S., & Peng, W. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581340 · Cited by 68 · cited 1×
“The humanness metaphor is realized through the creation of personas (also known as ‘system personas’ 3 ) and social role reproduction [41, 52].”
BackgroundSchiller, A., & McMahon, J. (2019) · New Political Science · doi:10.1080/07393148.2019.1595288 · Cited by 59 · cited 1×
“” They argue that historically, these roles have been occupied by women of color (treated as “physical absorbers” of “physical and affective dirt of a home” [68]).”
BackgroundThe potential of conversational agents to provide a rapid HIV counseling and testing services
van Heerden, A., Ntinga, X., & Vilakazi, K. (2017) · 2017 International Conference on the Frontiers and Advances in Data Science (FADS) · doi:10.1109/fads.2017.8253198 · Cited by 57 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundMeasuring Voice UX Quantitatively: A Rapid Review
Seaborn, K., & Urakami, J. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451712 · Cited by 55
Halperin, B. A., Hsieh, G., McElroy, E., Pierce, J., & Rosner, D. K. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581109 · Cited by 52 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundHey Google, Do You Have a Personality? Designing Personality and Personas for Conversational Agents
Pradhan, A., & Lazar, A. (2021) · Proceedings of the 3rd Conference on Conversational User Interfaces · doi:10.1145/3469595.3469607 · Cited by 50 · cited 2×
“Additionally, the presence of subordinate roles also implies the presence of “master” roles—a term loaded with unwanted connotations.”
BackgroundExtending Chatbots to Probe Users: Enhancing Complex Decision-Making Through Probing Conversations
Reicherts, L., Park, G. W., & Rogers, Y. (2022) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3543829.3543832 · Cited by 46 · cited 3×
“When it comes to finance, VUIs have been adopted for tasks such as providing customer support or enabling users to execute certain orders and transactions [65].”
BackgroundMethodBrokerbot: A Cryptocurrency Chatbot in the Social-technical Gap of Trust
Lee, M., Frank, L. E., & IJsselsteijn, W. A. (2021) · Computer Supported Cooperative Work (CSCW) · doi:10.1007/s10606-021-09392-6 · Cited by 45 · cited 2×
“ABSTRACT Voice User Interfaces (VUIs) increasingly leverage ‘humanness’ as a foundational design metaphor, adopting roles like ‘assistants,’ ‘teachers,’ and ‘secretaries’ to foster natural interactions.”
BackgroundJung, J.-Y., Qiu, S., Bozzon, A., & Gadiraju, U. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3517653 · Cited by 43 · cited 5×
“This finding is also supported by Pradhan et al. [62], who found older adults ontologically categorized VUIs as a person as well as an object (or something in between).”
BackgroundMethodResultInfluentialMetaphors in Voice User Interfaces: A Slippery Fish
Desai, S., & Twidale, M. (2023) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3609326 · Cited by 42 · cited 10×
“Desai & Twidale [24] developed a framework of metaphor contextualization in VUIs by identifying metaphors used by users in semi-structured interviews and VUI literature.”
BackgroundMethodInfluentialSelf-citationLupetti, M. L., Hagens, E., van der Maden, W., Steegers‐Theunissen, R. P. M., & Rousian, M. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597128 · Cited by 42 · cited 3×
“While users’ preferences regarding desired VUI personality may vary [78], it has been demonstrated that the type of VUI personality can directly impact users’ attitudes and interactions [49].”
BackgroundGenie in the Bottle: Anthropomorphized Perceptions of Conversational Agents
Kuzminykh, A., Sun, J., Govindaraju, N., Avery, J., & Lank, E. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376665 · Cited by 41 · cited 2×
“This choice was also informed by literature indicating the potential impact of voice gender on user perception [43].”
BackgroundDoes Chatbot Language Formality Affect Users’ Self-Disclosure?
Cox, S. R., & Ooi, W. T. (2022) · Proceedings of the 4th Conference on Conversational User Interfaces · doi:10.1145/3543829.3543831 · Cited by 41 · cited 1×
“Cox et al. [17] found that formal conversation style was perceived positively when conversation concerned managing sensitive health information or discussing patient’s lifestyle.”
BackgroundReimer, M. (1996) · Philosophical Studies · doi:10.1007/bf00355292 · Cited by 40 · cited 1×
“These metaphors are so ubiquitous in the language of computing that we have ceased to notice them [15], thereby becoming ‘dead’ metaphors [66].”
BackgroundDesai, S., & Chin, J. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581507 · Cited by 38
Self-citationArtificial Intelligence for Conversational Robo-Advisor
Day, M.-Y., Lin, J.-T., & Chen, Y.-C. (2018) · IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) · doi:10.1109/asonam.2018.8508269 · Cited by 38 · cited 1×
“In the investing context, conversational robo-advisors are a popular use case [11, 19, 32, 54].”
BackgroundThe influence of conversational agents on socially desirable responding
Schuetzler, R. M., Giboney, J. S., Grimes, G. M., & Nunamaker, J. F. (2018) · Proceedings of the Annual Hawaii International Conference on System Sciences · doi:10.24251/hicss.2018.038 · Cited by 37 · cited 2×
“Schuetzler et al. shown that even small differences in communication style such as increasing responsiveness can have significant impact on the quality of information gathered during the interview [69].”
BackgroundKocielnik, R., Langevin, R., George, J. S., Akenaga, S., Wang, A., Jones, D. P., Argyle, A., Fockele, C., Anderson, L., Hsieh, D. T., et al. (2021) · CUI 2021 - 3rd Conference on Conversational User Interfaces · doi:10.1145/3469595.3469599 · Cited by 37 · cited 1×
“Applications of VUIs in this area include: screening and monitoring [30, 42], consulting and advice [49, 77], learning [20], mental health support [53, 76], or healthy lifestyle advice [12, 29].”
BackgroundSadek, M., Calvo, R. A., & Mougenot, C. (2023) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3571884.3597143 · Cited by 37
TurtleTalk: An Educational Programming Game for Children with Voice User Interface
Jung, H., Kim, H. J., So, S., Kim, J., & Oh, C. (2019) · Extended Abstracts of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290607.3312773 · Cited by 33 · cited 3×
“Yet it is difficult to base technologies on humans because humans are very complicated.”
BackgroundAn Overview of Conversational Agent: Applications, Challenges and Future Directions
Alnefaie, A., Singh, S., Kocaballi, A. B., & Prasad, M. (2021) · International Conference on Web Information Systems and Technologies · doi:10.5220/0010708600003058 · Cited by 32 · cited 1×
“Health and finance are two popular application areas of VUIs [1].”
BackgroundPersuasive Synthetic Speech: Voice Perception and User Behaviour
Dubiel, M., Halvey, M., Gallegos, P. O., & King, S. (2020) · Proceedings of the 2nd Conference on Conversational User Interfaces · doi:10.1145/3405755.3406120 · Cited by 28 · cited 1×
“Given that prior research, such as Dubiel et al. [26, 27], has indicated that even minor variations in voice characteristics can significantly influence user perceptions, we decided to adopt a synthetic voice for the user role as well.”
ResultSelf-citationChin, J., Desai, S., Lin, S. (.-H., & Mejia, S. (2024) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3637365 · Cited by 27 · cited 1×
“Metaphors that signaled high competence were able to attract new users, but low competence metaphors were better evaluated and more likely to be adopted 3 https://developers.google.com/assistant/conversation-design/create-a-persona in the long term.”
BackgroundSelf-citationDesai, S., Lundy, M., & Chin, J. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597141 · Cited by 25 · cited 1×
“To this end, researchers and designers have deployed CUIs to fulfill various social roles, such as ‘teachers’ [20, 37], ‘coaches’ [21, 79], ‘storytellers’ [22], ‘brokers’ [45] or ‘therapists’ [56].”
Self-citationEnding the doctor-patient relationship in general practice: a proposed model
Stokes, T. (2004) · Family Practice · doi:10.1093/fampra/cmh506 · Cited by 21
Is Alexa like a computer? A search engine? A friend? A silly child? Yes.
Desai, S., & Twidale, M. (2022) · Proceedings of the 4th Conference on Conversational User Interfaces · doi:10.1145/3543829.3544535 · Cited by 20
Self-citationVölkel, S. T., Meindl, S., & Hussmann, H. (2021) · CUI 2021 - 3rd Conference on Conversational User Interfaces · doi:10.1145/3469595.3469605 · Cited by 16 · cited 1×
“While users’ preferences regarding desired VUI personality may vary [78], it has been demonstrated that the type of VUI personality can directly impact users’ attitudes and interactions [49].”
BackgroundTurk, V. (2016) · New Scientist · doi:10.1016/s0262-4079(16)32318-1 · Cited by 16
Impact of Voice Fidelity on Decision Making: A Potential Dark Pattern?
Dubiel, M., Sergeeva, A., & Leiva, L. A. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645202 · Cited by 16 · cited 1×
“Given that prior research, such as Dubiel et al. [26, 27], has indicated that even minor variations in voice characteristics can significantly influence user perceptions, we decided to adopt a synthetic voice for the user role as well.”
ResultSelf-citationCan Alexa be your Therapist?: How Back-Channeling Transforms Smart-Speakers to be Active Listeners
Motalebi, N., Cho, E., Sundar, S. S., & Abdullah, S. (2019) · Companion Publication of the 2019 Conference on Computer Supported Cooperative Work and Social Computing · doi:10.1145/3311957.3359502 · Cited by 15 · cited 2×
“ABSTRACT Voice User Interfaces (VUIs) increasingly leverage ‘humanness’ as a foundational design metaphor, adopting roles like ‘assistants,’ ‘teachers,’ and ‘secretaries’ to foster natural interactions.”
BackgroundWei, C. Z., Kim, Y.-H., & Kuzminykh, A. (2023) · Proceedings of the 5th International Conference on Conversational User Interfaces · doi:10.1145/3571884.3597139 · Cited by 14 · cited 2×
“You can also adjust the coverage amount based on your most critical financial needs to find a balance between sufficient coverage and affordability. two items on 7-point Likert scale: “If available, I intend to start using Z within the next month,” and “If available, in the next months, I plan to…”
BackgroundMethodDesai, S., Hu, X., Lundy, M., & Chin, J. (2023) · International Conference on Human-Agent Interaction · doi:10.1145/3623809.3623827 · Cited by 13
Self-citationLeaving the Butler Behind: The Future of Role Reproduction in CUI
McMillan, D., & Jaber, R. (2021) · CUI 2021 - 3rd Conference on Conversational User Interfaces · doi:10.1145/3469595.3469606 · Cited by 8 · cited 3×
“These and other ethical and functional concerns have been well documented in previous CUI conferences [23, 28, 52, 63, 72].”
BackgroundShoehorning in the name of science
Edlund, J. (2019) · Proceedings of the 1st International Conference on Conversational User Interfaces · doi:10.1145/3342775.3342794 · Cited by 6 · cited 3×
“These and other ethical and functional concerns have been well documented in previous CUI conferences [23, 28, 52, 63, 72].”
BackgroundShould Alexa be a Police Officer, a Doctor, or a Priest?: Towards CUI Relationships Worth Having
Simpson, J., & Crone, C. (2022) · Proceedings of the 4th Conference on Conversational User Interfaces · doi:10.1145/3543829.3544522 · Cited by 6 · cited 2×
“…in CUI’21, Pradhan & Lazar [63] raised the ethical issues with designing human-like personas, highlighting how the default voices of commercial VUIs often resemble “white women from the West” and emphasized that crafting female personas in subordinate roles can perpetuate existing societal biases.”
Background
Research works printed but not linked: 4
- Heloisa Candello, Claudio Pinhanez, David Millen, and Bruna Daniele Andrade. 2017. Shaping the experience of a cognitive investment adviser. In Design, User Experience, and Usability: Understanding Users and Contexts: 6th International Conference, DUXU 2017, Held as Part of HCI International 2017, Vancouver, BC, Canada, July 9-14, 2017, Proceedings, Part III 6. Springer, 594–613.
- Amanda Cercas Curry, Judy Robertson, and Verena Rieser. 2020. Conversational assistants and gender stereotypes: Public perceptions and desiderata for voice personas. In Proceedings of the second workshop on gender bias in natural language processing. 72–78.
- George Lakoff and Mark Johnson. 1980. Metaphors We Live By. University of Chicago Press. Google-Books-ID: r6nOYYtxzUoC.
- Don Norman. 2013. The Design Of Everyday Things (revised edition ed.). Basic Books, New York, New York.
Cited by
Designing AI Personalities: Enhancing Human-Agent Interaction Through Thoughtful Persona Design
Zargham, N., Dubiel, M., Desai, S., Mildner, T., & Belz, H.-J. (2024) · International Conference on Mobile and Ubiquitous Multimedia (MUM) · doi:10.1145/3701571.3701608 · Cited by 21
“Additionally, Desai et al. [7] found that the choice of persona also affects the perceived trust, likeability, and intention to adopt.”
BackgroundSelf-citationBeyond Functionality: Co-Designing Voice User Interfaces for Older Adults' Well-being
Hu, X., Desai, S., Lundy, M., & Chin, J. (2025) · ACM Conference on Conversational User Interfaces (CUI) · doi:10.1145/3719160.3736613 · Cited by 23
Self-citationExploring Older Adults Personality Preferences for LLM-powered Conversational Companions
Shahid, A., Chung, J., & Heo, S. (2025) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3706599.3719976 · Cited by 15
Sun, X., Liu, Y., Bosch, J. A., & Li, Z. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711014 · Cited by 18
“Desai et al. [45] indicate a preference for the human metaphor over the non-human in health contexts for its perceived enjoyability and likeability, but not for trust.”
Unboxing Manipulation Checks for Voice UX
Seaborn, K., Rogers, K., Altmeyer, M., Watanabe, M., Sawa, Y., Nam, S., Itagaki, T., & Li, G. (2024) · Interacting with Computers · doi:10.1093/iwc/iwae062 · Cited by 13
Metadata
- Authors
- Desai, S., Dubiel, M., & Leiva, L. A.
- Affiliations
- Northeastern University (US)
- University of Luxembourg (LU)
- Venue
- ACM Conversational User Interfaces 2024
- Publisher
- ACM
- Published
- 2024-07-08
- Pages
- 1-15
- OpenAlex
- W4400397492
- Semantic Scholar
- 1f9309be206711ca1c2808be1df82d9e278d3d74
- Cited by
- 21
- References
- 73
- Citations by year
- 2026: 9 · 2025: 10 · 2024: 2
- FWCI
- 6.21
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Conversational User Interfaces (CUI) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- Open Repository and Bibliography (University of Luxembourg) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Horizon 2020 (CHIST-ERA-20-BCI-001)
- European Innovation Council and Small and Medium-sized Enterprises Executive Agency (101071147)
- Topics
- Social Sciences › Business, Management and Accounting › Marketing › AI in Service Interactions
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Human-Computer Interaction › Innovative Human-Technology Interaction
- Keywords
- voice user interface, design metaphor, user trust, social stereotypes, adoption intention, health domain, conversational design, metaphor awareness, user engagement
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
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.