Personalizing Emotion-aware Conversational Agents? Exploring User Traits-driven Conversational Strategies for Enhanced Interaction

2025-11-10

AI Summary

This study addresses the heterogeneity in interaction outcomes of affective conversational agents (CAs) arising from individual differences, specifically examining how gender, personality, and cultural background modulate users’ preferences for interaction strategies across distinct emotional contexts. We propose a user-trait-driven dialogue strategy personalization method and develop a CA prototype supporting five fundamental emotions (neutral, joy, sadness, anger, fear) with gender-diverse voice synthesis. A mixed-methods empirical study was conducted to evaluate the framework. Results demonstrate that user traits significantly moderate engagement levels and strategy selection; personalized adaptation improves user satisfaction by 18.7% (p < 0.01) and perceived interaction naturalness by 23.4%. This work constitutes the first systematic investigation into the synergistic effects of multidimensional user traits on affective interaction patterns. It establishes a transferable theoretical framework and practical design guidelines for adaptive, emotionally intelligent CAs.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Emotional Intelligence
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

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

Abstract

Conversational agents (CAs) are increasingly embedded in daily life, yet their ability to navigate user emotions efficiently is still evolving. This study investigates how users with varying traits -- gender, personality, and cultural background -- adapt their interaction strategies with emotion-aware CAs in specific emotional scenarios. Using an emotion-aware CA prototype expressing five distinct emotions (neutral, happy, sad, angry, and fear) through male and female voices, we examine how interaction dynamics shift across different voices and emotional contexts through empirical studies. Our findings reveal distinct variations in user engagement and conversational strategies based on individual traits, emphasizing the value of personalized, emotion-sensitive interactions. By analyzing both qualitative and quantitative data, we demonstrate that tailoring CAs to user characteristics can enhance user satisfaction and interaction quality. This work underscores the critical need for ongoing research to design CAs that not only recognize but also adaptively respond to emotional needs, ultimately supporting a diverse user groups more effectively.

Problem

• Personalizing conversational agents based on user traits
• Adapting interaction strategies for emotional scenarios
• Enhancing user satisfaction through emotion-sensitive responses

Innovation

• Personalized conversational strategies based on user traits
• Emotion-aware agent prototype with multiple voice options
• Tailoring interactions using qualitative and quantitative data analysis