Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

"Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations

Niharika Mathur, Hasibur Rahman, Smit Desai

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.

"Who wants to be nagged by AI?": Investigating the Effects of Agreeableness on Older Adults' Perception of LLM-Based Voice Assistants' Explanations

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.
Paper Structure (12 sections, 2 figures)

This paper contains 12 sections, 2 figures.

Table of Contents

  1. Introduction
  2. Related Work and Background
  3. Method
  4. Participants
  5. Procedure
  6. Results
  7. LLM-VA Agreeableness and Explanation Perception (RQ1)
  8. Context and Explanation Type Effects (RQ2)
  9. User Agreeableness and Explanation Perception (RQ3)
  10. Qualitative perceptions
  11. Discussion
  12. Conclusion

Figures (2)

  • Figure 1: Interactive storyboard UI and sequence (A$\rightarrow$B$\rightarrow$C). Participants clicked the $\blacktriangleright$ button to play the reminder or alert (A) and then the explanation (B). After each audio clip, a $\blacksquare$ speech bubble displayed the transcript (B)(C).
  • Figure 2: Ratings for LA versus HA Robin across seven outcomes. Asterisks mark significant LA–HA differences from Kruskal-Wallis tests (*$p<.05$, **$p<.01$). Intention to adopt and empathy are shown on 1 to 7 scales, with empathy scores rescaled for this visualization only. Trust, reliance, satisfaction, likeability, and intelligence are shown on 1 to 5 scales.