Exploring the Design of LLM-based Agent in Enhancing Self-disclosure Among the Older Adults

要旨

Social difficulties have become an increasingly serious issue among older adults. For older adults, regular self-disclosure is essential for maintaining mental health and building close relationships. Leveraging conversational agents to encourage self-disclosure in older adults has shown increasing potential. Understanding how LLM-based agents can influence and stimulate self-disclosure across different topics is crucial for designing future agents tailored to older users. This study introduces Disclosure-Agent, an LLM-based conversational agent, and examines its impact on self-disclosure in older adults through a user study involving 20 participants, 8 topics, and two interactive interfaces equipped with Disclosure-Agent. The findings provide valuable insights into how LLM-based agents can promote self-disclosure in older adults and offer design recommendations for future elderly-oriented conversational agents.

著者
Yijie Guo
Tsinghua University, Beijing, China
Ruhan Wang
Tsinghua University, Beijing, China
Zhenhan Huang
University of Tsukuba, Tsukuba, Japan
Tongtong Jin
Tsinghua University, Beijing, China
Xiwen Yao
Tsinghua University, Beijing, China
Yuan-Ling Feng
Tsinghua University, Beijing, Haidian, China
Weiwei Zhang
School of Digital Media & Design Arts, Beijing, --- Select One ---, China
Yuan Yao
School of Architecture and Design, Beijing, Beijing, China
Haipeng Mi
Tsinghua University, Beijing, China
DOI

10.1145/3706598.3713639

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713639

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: Digital Health for Different User Needs

G314+G315
7 件の発表
2025-04-30 20:10:00
2025-04-30 21:40:00
日本語まとめ
読み込み中…