The Differential Effects of Agreeableness and Extraversion on Older Adults' Perceptions of Conversational AI Explanations in Assistive Settings

TL;DR

Results reveal that high agreeableness drove stronger empathy perceptions, while low agreeableness consistently penalized likeability, suggesting that personality shapes sociability without altering competence perceptions.

Abstract

Large Language Model-based Voice Assistants (LLM-VAs) are increasingly deployed in assistive settings for older adults, yet little is known about how an agent's personality shapes user perceptions of its explanations. This paper presents a mixed factorial experiment (N=140) examining how agreeableness and extraversion in an LLM-VA ("Robin") influence older adults' perceptions across seven measures: empathy, likeability, trust, reliance, satisfaction, intention to adopt, and perceived intelligence. Results reveal that high agreeableness drove stronger empathy perceptions, while low agreeableness consistently penalized likeability. Importantly, perceived intelligence remained unaffected by personality, suggesting that personality shapes sociability without altering competence perceptions. Real-time environmental explanations outperformed conversational history explanations on five measures, with advantages concentrated in emergency contexts. Notably, highly agreeable participants were especially critical of low-agreeableness agents, revealing a user-agent personality congruence effect. These findings offer design implications for personality-aware, context-sensitive LLM-VAs in assistive settings.

Figures (12)

• 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: Outcome measures across four LLM-VA personality conditions (LA, HA, LE, HE). Violin plots show distributions with individual ratings; lines indicate medians. Panel titles show Kruskal--Wallis significance (KW). Brackets mark significant Holm-corrected Mann--Whitney $U$ comparisons ($^{*}p_{\mathrm{adj}}<.05$, $^{**}p_{\mathrm{adj}}<.01$, $^{***}p_{\mathrm{adj}}<.001$); bracket color indicates the higher-mean condition.
• Figure 3: Boxplots of all seven measures by explanation types (UH vs. ENV) for the Low Agreeableness (LA) and High Agreeableness (HA) conditions.
• Figure 4: Boxplots of all seven measures by explanation types (UH vs. ENV) for the Low Extraversion (LE) and High Extraversion (HE) conditions.
• Figure 5: Boxplots of all seven measures by context (Routine reminders vs. Emergency alerts) for the Low Agreeableness (LA) and High Agreeableness (HA) conditions.