The DOI matches its Crossref record; 64 of the 70 references it cites were found in a registry or an index; 7 of the 19 sources its claims cite were checked for support.
"Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations
Open accessAbstract
LLM-based voice assistants (VAs) increasingly support older adults aging in place, yet how an assistant’s agreeableness shapes explanation perception remains underexplored. We conducted a study (N=70) examining how VA agreeableness influences older adults’ perceptions of explanations across routine and emergency home scenarios. High-agreeableness assistants were perceived as more trustworthy, empathetic, and likable, but these benefits diminished in emergencies where clarity outweighed warmth. Agreeableness did not affect perceived intelligence, suggesting social tone and competence are separable dimensions. Real-time environmental explanations outperformed history-based ones, and agreeable older adults penalized low-agreeableness assistants more strongly. These findings show the need to move beyond a one-size-fits-all approach to AI explainability, while balancing personality, context, and audience.
Overview
CoChat Summary
## TL;DR
This controlled study with 70 older adults found that high-agreeableness LLM voice assistants were generally perceived more positively than low-agreeableness ones, especially for trust, empathy, likeability, and adoption. The benefits of agreeableness weakened in emergency contexts, and real-time environmental explanations were often preferred over history-based explanations.
## Key findings
- With 70 U.S.-based older adults (ages 60–83, M = 65.97, SD = 5.28), participants rated the high-agreeableness assistant as significantly more agreeable than the low-agreeableness one (HA M = 4.171 vs. LA M = 3.229, t = -4.093, p = .0001).
- High agreeableness improved several explanation perceptions: intention to adopt (Mdn = 5.75 vs. 5.25, H = 5.299, p = .021, |r| = .275), empathy (59.32 vs. 38.16, H = 7.394, p = .006, |r| = .325), likeability (4.25 vs. 3.40, H = 7.188, p = .007, |r| = .320), trust (3.75 vs. 3.35, H = 5.666, p = .017, |r| = .285), reliance (3.85 vs. 3.45, H = 5.013, p = .025, |r| = .268), and satisfaction (4.07 vs. 3.75, H = 4.624, p = .032, |r| = .257).
- Agreeableness did not significantly affect perceived intelligence (H = 0.134, p = .715, |r| = .044).
- Context and explanation type mattered: the high-agreeableness assistant had a broader advantage in routine reminders than in emergency alerts, and real-time environmental explanations were generally preferred over history-based ones for reliance, satisfaction, likeability, and intelligence.
## Methods
- The study used a 2 × 2 × 2 mixed factorial design with three manipulated factors: explanation type (conversational history vs. real-time environmental data), LLM-VA agreeableness (high vs. low; between-subjects), and interaction context (routine vs. emergency; within-subjects).
- Participants were 70 U.S.-based older adults recruited through Prolific; they were aged 60–83 and interacted with a fictional assistant named Robin via vignette-based interactive storyboards.
- Analysis used nonparametric tests because none of the outcomes were normally distributed: Kruskal-Wallis tests for between-group comparisons and Wilcoxon tests for within-subject comparisons; correlations with participant agreeableness were also examined.
## Limitations
- The paper states that it examined only a single personality dimension, agreeableness, and used a binary manipulation, so it did not capture the full range of personality expression in conversational AI.
- The storyboard-based design relied on a single synthetic voice, limiting insight into how vocal tone and prosody interact with personality, and into longitudinal dynamics or repeated failures in real-world use.
- The scenarios were presented in a controlled setting, so in-situ deployments are still needed to understand how the effects evolve with sustained real-world use.
- Evident from the text: the study used fictional, storyboard-based interactions rather than live deployments, so ecological validity may be limited.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
5 Valid · 1 Not valid · 6 Not checked · 57 Own results and interpretations
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“In response to RQ3, we found an interesting association between older adults' agreeableness and their perceptions of Robin 's explanations: more agreeable older adults penalized the LA Robin more.”
- Also stated in: § 5 Discussion Design Considerations. Our findings extend prior work on conversational AI personality and explainability, suggesting five design considerations (DCs). DC1: Consistent with Völkel and Kaya [62], who found users prefer agreeableness contextually rather than universally, our results demonstrate that effective explanations require sensitivity to context, grounding, and audience, not a fixed conversational style. DC2: High agreeableness improved trust, empathy, and adoption in routine contexts, but these benefits diminished in emergencies, supporting Kim and Fussell [31]'s findings that agreeableness effects are task-dependent and suggesting clarity may outweigh warmth in high-stakes scenarios. DC3: Agreeableness increased likeability without affecting perceived intelligence, indicating these are separable design dimensions. This extends Khadpe et al. [29]'s work on conceptual metaphors and suggests designers can modulate warmth independently of competence signaling, critical for avoiding sycophancy concerns in LLMs [61]. DC4: Real-time environmental explanations were perceived as more credible than history-based ones, echoing Mathur et al. [40]'s emphasis on situationally anchored information for older adults and suggesting data-driven grounding may better support trust calibration than personalization alone. DC5: More agreeable older adults penalized low-agreeableness assistants more strongly, extending personality-matching research [6, 57, 62] to the explanation domain. Collectively, these findings position AI explanation design as a joint problem of content, delivery, and audience, reinforcing that one-size-fits-all approaches are insufficient for older adults across diverse assistive scenarios. Limitations and Future Work. In this study, we examined a single personality dimension, agreeableness, using a binary manipulation that enabled controlled comparison but did not capture the full range of personality expression in conversational AI. Future work should examine additional traits, such as emotional stability and conscientiousness. Our storyboard-based design relied on a single synthetic voice, limiting insight into how vocal tone and prosody interact with personality, as well as longitudinal dynamics or the impact of repeated system failures in-the-wild. Finally, our scenarios were presented in a controlled setting, and in-situ deployments are needed to understand how these effects evolve with sustained real-world use. · plain
“DC5: More agreeable older adults penalized low-agreeableness assistants more strongly, extending personality-matching research [6, 57, 62] to the explanation domain.”
What the sources say
- Could not verifycites [6] [6] Jessie Chin, Smit Desai, Sheny Lin, and Shannon Mejia. 2024. Like my aunt dorothy: effects of conversational styles on perceptions, acceptance and metaphorical descriptions of voice assistants during later adulthood. Proceedings of the ACM on Human-Computer Interaction 8, CSCW1 (2024), 1-21. - sourceExperimental — accuracy not yet measured
Section 5.1 (p. 11) reports that older adults with higher agreeableness rated a voice assistant as more likeable; the Discussion (p. 16) reiterates that finding. Searches for Robin, LA Robin, and perceptions of explanations found no passage about agreeable older adults penalizing LA Robin. (LLM, conf=0.76)
- Could not verifycites [57] [57] Hasibur Rahman and Smit Desai. 2025. Vibe Check: Understanding the Effects of LLM-Based Conversational Agents' Personality and Alignment on User Perceptions in Goal-Oriented Tasks. doi:10.48550/arXiv.2509.09870 arXiv:2509.09870 [cs]. - sourceExperimental — accuracy not yet measured
Section 4.3 (p. 14) reports associations between user–agent agreeableness distance and ratings of enjoyment, intention to adopt, and trust. It does not report whether more agreeable older adults rated a low-alignment Robin's explanations more negatively; searches for Robin and that age-specific association found no such passage. (LLM, conf=0.77)
- Not checked — no full text of the sourcecites [62] [62] Sarah Theres Völkel and Lale Kaya. 2021. Examining user preference for agreeableness in chatbots. In Proceedings of the 3rd Conference on Conversational User Interfaces . 1-6. - source
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.
- Also stated in: § 5 Discussion Design Considerations. Our findings extend prior work on conversational AI personality and explainability, suggesting five design considerations (DCs). DC1: Consistent with Völkel and Kaya [62], who found users prefer agreeableness contextually rather than universally, our results demonstrate that effective explanations require sensitivity to context, grounding, and audience, not a fixed conversational style. DC2: High agreeableness improved trust, empathy, and adoption in routine contexts, but these benefits diminished in emergencies, supporting Kim and Fussell [31]'s findings that agreeableness effects are task-dependent and suggesting clarity may outweigh warmth in high-stakes scenarios. DC3: Agreeableness increased likeability without affecting perceived intelligence, indicating these are separable design dimensions. This extends Khadpe et al. [29]'s work on conceptual metaphors and suggests designers can modulate warmth independently of competence signaling, critical for avoiding sycophancy concerns in LLMs [61]. DC4: Real-time environmental explanations were perceived as more credible than history-based ones, echoing Mathur et al. [40]'s emphasis on situationally anchored information for older adults and suggesting data-driven grounding may better support trust calibration than personalization alone. DC5: More agreeable older adults penalized low-agreeableness assistants more strongly, extending personality-matching research [6, 57, 62] to the explanation domain. Collectively, these findings position AI explanation design as a joint problem of content, delivery, and audience, reinforcing that one-size-fits-all approaches are insufficient for older adults across diverse assistive scenarios. Limitations and Future Work. In this study, we examined a single personality dimension, agreeableness, using a binary manipulation that enabled controlled comparison but did not capture the full range of personality expression in conversational AI. Future work should examine additional traits, such as emotional stability and conscientiousness. Our storyboard-based design relied on a single synthetic voice, limiting insight into how vocal tone and prosody interact with personality, as well as longitudinal dynamics or the impact of repeated system failures in-the-wild. Finally, our scenarios were presented in a controlled setting, and in-situ deployments are needed to understand how these effects evolve with sustained real-world use. · plain
Every source the paper cites for this claim was checked and supports it.
In the paper
“echoing Mathur et al. [40]'s emphasis on situationally anchored information for older adults”
What the sources say
- Supportedcites [40] [40] Niharika Mathur, Tamara Zubatiy, Agata Rozga, Jodi Forlizzi, and Elizabeth Mynatt. 2025. " Sometimes You Need Facts, and Sometimes a Hug": Understanding Older Adults' Preferences for Explanations in LLM-Based Conversational AI Systems. arXiv preprint arXiv:2510.06697 (2025). - source
The Results in 4.2 (p. 11) state that older adult participants 'consistently favored explanations grounded in real-time environmental data and inferences drawn from them, valuing them for their concreteness and situational relevance,' and rejected explanations carrying no knowledge about them. The design considerations (5.1, p. 15 and 5.1.2, p. 15) likewise call for explanations with contextual references to conversational memory, emotional state and the broader sociotechnical environment, and for explicitly encoding context of use. Wording differs ('situationally anchored' vs. 'grounded/situationally relevant/contextually grounded'), but the attributed emphasis is present. (LLM, conf=0.86)
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.
- Supported
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
“Kruskal-Wallis tests showed that HA outperformed LA across more measures in Ctx1 ( intention to adopt, empathy, trust, reliance, satisfaction, likeability ; all 𝑝 < . 05) than in Ctx2 (only i ntention to adopt, empathy, likeability ; all 𝑝 < . 05).”
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.
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
“ENV explanations outperformed UH on reliance, satisfaction, likeability, and intelligence (all 𝑝 < . 05).”
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.
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
“HA's advantage was broader for UH explanations (all measures except intelligence , 𝑝 < . 05)”
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.
44 more claims
Create a free account to see all 69 claims and to verify the 3 references still open.
- Probably not a substantial claim. 15
- It may state two separate claims as one. 8
Citations
Cites
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302 · cited 2×
“Research in explainable AI (XAI) has largely focused on mechanistic interpretations of AI models, often emphasizing internal model logic and decision factors [43].”
The structure of phenotypic personality traits.
Goldberg, L. R. (1993) · American Psychologist · doi:10.1037/0003-066x.48.1.26 · Cited by 4,816
Bartneck, C., Kulić, D., Croft, E., & Zoghbi, S. (2009) · International Journal of Social Robotics · doi:10.1007/s12369-008-0001-3 · Cited by 3,193
The Mini-IPIP Scales: Tiny-yet-effective measures of the Big Five Factors of Personality.
Donnellan, M. B., Oswald, F. L., Baird, B. M., & Lucas, R. E. (2006) · Psychological Assessment · doi:10.1037/1040-3590.18.2.192 · Cited by 2,442
Foundations 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
John, O. P., Donahue, E. M., & Kentle, R. L. (2012) · PsycTESTS Dataset · doi:10.1037/t07550-000 · Cited by 971
Digital family portraits: supporting peace of mind for extended family members
Mynatt, E. D., Rowan, J., Craighill, S., & Jacobs, A. (2001) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/365024.365126 · Cited by 582
Pradhan, A., Mehta, K., & Findlater, L. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174033 · Cited by 448 · cited 1×
“When people interact with VAs, they often seek social engagement [47, 55], and evaluate VAs based on its personality cues [8, 18, 65].”
How 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
From interaction to trajectories: designing coherent journeys through user experiences
Benford, S., Giannachi, G., Koleva, B., & Rodden, T. (2009) · Proceedings of the SIGCHI Conference on Human Factors in Computing Systems · doi:10.1145/1518701.1518812 · Cited by 314
Research works printed but not linked: 1
- Hasibur Rahman and Smit Desai. 2025. Vibe Check: Understanding the Effects of LLM-Based Conversational Agents’ Personality and Alignment on User Perceptions in Goal-Oriented Tasks. 10.48550/arXiv.2509.09870arXiv:https://arXiv.org/abs/2509.09870. · DOI · Paper page
Cited by
Kinoshita, Y., & Nakamura, S. (2026) · Nordic Conference on Human-Computer Interaction · doi:10.1145/3829807.3829876
Metadata
- Authors
- Mathur, N., Rahman, H., & Desai, S.
- Affiliations
- Georgia Institute of Technology (US)
- Northeastern University (US)
- Venue
- Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2026-04-13
- Pages
- 1-6
- OpenAlex
- W7134915560
- Cited by
- 1
- References
- 65
- Citations by year
- 2026: 1
- FWCI
- 13.45
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University)
- 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 › Explainable Artificial Intelligence (XAI)
- Keywords
- agreeableness, older adults, explainable AI, trust in AI, empathy, aging in place, emergency situations, perceived intelligence
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 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and 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: "Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations. https://app.cochat.ai/papers/10.1145/3772363.3798685
- The paper
- Mathur, N., Rahman, H., & Desai, S. (2026). "Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations. Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems. https://doi.org/10.1145/3772363.3798685
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.