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

2026-03-09

AI Summary

This study investigates how the personality traits—specifically agreeableness and extraversion—of large language model–based voice assistants influence older adults’ perceptions, acceptance, and trust in system-generated explanations. Through a mixed-factor experiment (N=140), the authors evaluated different personality variants of a voice assistant named “Robin” across seven perceptual dimensions and compared the effectiveness of real-time contextual explanations against those based on dialogue history. Results indicate that high agreeableness significantly enhances perceived empathy and likability, and that personality consistency affects user evaluations, though personality traits do not impact perceived intelligence. Furthermore, real-time contextual explanations outperformed dialogue-history-based explanations on five of the seven metrics, particularly in emergency scenarios. These findings offer empirical support and novel design insights for developing personalized, context-aware AI assistants tailored to older users.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Intelligent Robots: Human-Robot Interaction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

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.

Problem

• Conversational AI
• Older Adults
• Personality Traits
• Explainability
• Assistive Technology

Innovation

• personality-aware AI
• conversational explanations
• older adults
• large language model voice assistants
• user-agent congruence