Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

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 access
Mathur, Niharika, Rahman, Hasibur, Desai, Smit · 2026 · Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems

Abstract

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

Crossref · 10.1145/3772363.3798685

Cites

64 of 70 references verified0 citation errors · 6 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

5 Valid · 1 Not valid · 6 Not checked · 57 Own results and interpretations

44 more claims

Create a free account to see all 69 claims and to verify the 3 references still open.

See all claims — free account
  • Probably not a substantial claim. 15
  • It may state two separate claims as one. 8

Create a free account to see these claims.

Citations

Cites

Research works printed but not linked: 1

  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

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
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

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.