Customizing Emotional Support: How Do Individuals Construct and Interact With LLM-Powered Chatbots

2025-04-17

AI Summary

This study addresses the challenge of designing personalized, emotionally supportive chatbots powered by large language models (LLMs) that adapt to heterogeneous user needs in emotional dependency, stress coping, and self-reflection. Method: We conducted a one-week field study with 22 participants using ChatLab—a multimodal platform enabling voice interaction, embodied avatars, prompt engineering, and dynamic memory regulation. Contribution/Results: We systematically uncover how users actively co-construct bot personas to foster trust, identifying five distinct usage patterns; 91% reported increased conversational openness and honesty. The study introduces novel personalization mechanisms—including adjustable memory persistence and cross-platform activity integration—and yields 12 actionable design opportunities. These findings advance both theoretical understanding and practical implementation of LLM-based mental health support systems.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Safety and Robustness
• Intelligent Robots: Embodied AI

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Personalized support is essential to fulfill individuals' emotional needs and sustain their mental well-being. Large language models (LLMs), with great customization flexibility, hold promises to enable individuals to create their own emotional support agents. In this work, we developed ChatLab, where users could construct LLM-powered chatbots with additional interaction features including voices and avatars. Using a Research through Design approach, we conducted a week-long field study followed by interviews and design activities (N = 22), which uncovered how participants created diverse chatbot personas for emotional reliance, confronting stressors, connecting to intellectual discourse, reflecting mirrored selves, etc. We found that participants actively enriched the personas they constructed, shaping the dynamics between themselves and the chatbot to foster open and honest conversations. They also suggested other customizable features, such as integrating online activities and adjustable memory settings. Based on these findings, we discuss opportunities for enhancing personalized emotional support through emerging AI technologies.

Problem

• How to customize LLM-powered chatbots for emotional support
• Exploring user interaction with personalized chatbot personas
• Enhancing emotional well-being through AI-driven customizable features

Innovation

• Users construct personalized LLM-powered emotional support chatbots
• ChatLab integrates voices and avatars for enhanced interaction
• Customizable features include online activities and memory settings