CharacterChat: Learning towards Conversational AI with Personalized Social Support

TL;DR

CharacterChat introduces a personalized social support conversational system that leverages persona-based virtual supporters and interpersonal matching to enhance mental well-being support.

Contribution

The paper presents the S2Conv framework, the MBTI-1024 Bank, and CharacterChat, a system integrating persona-driven conversations with interpersonal matching for personalized support.

Findings

CharacterChat effectively provides personalized social support.

Interpersonal matching significantly improves support quality.

The system demonstrates strong potential for mental well-being applications.

Abstract

In our modern, fast-paced, and interconnected world, the importance of mental well-being has grown into a matter of great urgency. However, traditional methods such as Emotional Support Conversations (ESC) face challenges in effectively addressing a diverse range of individual personalities. In response, we introduce the Social Support Conversation (S2Conv) framework. It comprises a series of support agents and the interpersonal matching mechanism, linking individuals with persona-compatible virtual supporters. Utilizing persona decomposition based on the MBTI (Myers-Briggs Type Indicator), we have created the MBTI-1024 Bank, a group that of virtual characters with distinct profiles. Through improved role-playing prompts with behavior preset and dynamic memory, we facilitate the development of the MBTI-S2Conv dataset, which contains conversations between the characters in the MBTI-1024 Bank. Building upon these foundations, we present CharacterChat, a comprehensive S2Conv system, which includes a conversational model driven by personas and memories, along with an interpersonal matching plugin model that dispatches the optimal supporters from the MBTI-1024 Bank for individuals with specific personas. Empirical results indicate the remarkable efficacy of CharacterChat in providing personalized social support and highlight the substantial advantages derived from interpersonal matching. The source code is available in \url{https://github.com/morecry/CharacterChat}.