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; 7 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
7 Valid · 2 Not valid · 40 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
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.
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
“Importantly, our research reveals that the explicit awareness of a metaphor’s use influences adoption intentions”
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.
47 more claims
Create a free account to see all 101 claims and to verify the 51 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].”
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Examining Humanness as a Metaphor to Design Voice User Interfaces. https://app.cochat.ai/papers/10.1145/3640794.3665535
- The paper
- Desai, S., Dubiel, M., & Leiva, L. A. (2024). Examining Humanness as a Metaphor to Design Voice User Interfaces. ACM Conversational User Interfaces 2024. https://doi.org/10.1145/3640794.3665535
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.