Beyond the Dialogue: Multi-chatbot Group Motivational Interviewing for Premenstrual Syndrome (PMS) Management

要旨

Premenstrual syndrome (PMS) is a prevalent disorder among women, often exacerbated by a lack of peer support due to associated stigmatization. Drawing inspiration from the established benefits of group therapy, particularly the sense of belonging it fosters, we developed a multi-chatbot group motivational interviewing system. The system consists of a facilitator bot and two peer bots, and simulates a group counseling environment for PMS management using Large Language Models (LLMs). We conducted a study with 63 participants and divided them into three conditions (no intervention, 1-on-1 chatbot, group chatbots) over two menstruation cycles for evaluation. Our findings revealed that participants in the group chat condition exhibited higher levels of engagement and language convergence with the chatbots. These participants were also able to engage in social learning and demonstrated motivation in coping through interactions with the chatbots. Finally, we discuss design implications for multi-chatbot interactions in supporting mental health.

著者
Shixian Geng
The University of Tokyo, Tokyo, Japan
Remi Inayoshi
The University of Tokyo, Tokyo, Japan
Chi-Lan Yang
The University of Tokyo, Tokyo, Japan
Zefan Sramek
The University of Tokyo, Tokyo, Japan
Yuya Umeda
The University of Tokyo, Tokyo, Japan
Chiaki Kasahara
Ochanomizu University, Tokyo, Japan
Arissa J. Sato
University of Wisconsin-Madison, Madison, Wisconsin, United States
Simo Hosio
University of Oulu, Oulu, Oulu, Finland
Koji Yatani
University of Tokyo, Tokyo, Japan
DOI

10.1145/3706598.3713918

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713918

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: LLM for Health

Annex Hall F206
6 件の発表
2025-04-30 18:00:00
2025-04-30 19:30:00
日本語まとめ
読み込み中…