Exploring Modular Prompt Design for Emotion and Mental Health Recognition

要旨

Recent advances in large language models (LLM) offered human-like capabilities for comprehending emotion and mental states. Prior studies explored diverse prompt engineering techniques for improving classification performance, but there is a lack of analysis of prompt design space and the impact of each component. To bridge this gap, we conduct a qualitative thematic analysis of existing prompts for emotion and mental health classification tasks to define the key components for prompt design space. We then evaluate the impact of major prompt components, such as persona and task instruction, on classification performance by using four LLM models and five datasets. Modular prompt design offers new insights into examining performance variability as well as promoting transparency and reproducibility in LLM-based tasks within health and well-being intervention systems.

著者
Minseo Kim
Hankuk University of Foreign Studies, Seoul, Korea, Republic of
Taemin Kim
Hansung University, Seoul, Korea, Republic of
Thu Hoang Anh. Vo
Korea Advanced Institute of Science & Technology, Daejeon, Korea, Republic of
Yugyeong Jung
KAIST, Daejeon, Korea, Republic of
Uichin Lee
KAIST, Daejeon, Korea, Republic of
DOI

10.1145/3706598.3713888

論文URL

https://dl.acm.org/doi/10.1145/3706598.3713888

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: Well-being and Data Tracking

G414+G415
5 件の発表
2025-04-30 23:10:00
2025-05-01 00:40:00
日本語まとめ
読み込み中…