Examining AI Methods for Micro-Coaching Dialogs

要旨

Conversational interaction, for example through chatbots, is well-suited to enable automated health coaching tools to support self-management and prevention of chronic diseases. However, chatbots in health are predominantly scripted or rule-based, which can result in a stagnant and repetitive user experience in contrast with more dynamic, data-driven chatbots in other domains. Consequently, little is known about the tradeoffs of pursuing data-driven approaches for health chatbots. We examined multiple artificial intelligence (AI) approaches to enable micro-coaching dialogs in nutrition — brief coaching conversations related to specific meals, to support achievement of nutrition goals — and compared, reinforcement learning (RL), rule-based, and scripted approaches for dialog management. While the data-driven RL chatbot succeeded in shorter, more efficient dialogs, surprisingly the simplest, scripted chatbot was rated as higher quality, despite not fulfilling its task as consistently. These results highlight tensions between scripted and more complex, data-driven approaches for chatbots in health.

著者
Elliot G. Mitchell
Columbia University, New York, New York, United States
Noemie Elhadad
Columbia University, New York, New York, United States
Lena Mamykina
Columbia University, New York, New York, United States
論文URL

https://dl.acm.org/doi/abs/10.1145/3491102.3501886

動画

会議: CHI 2022

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2022.acm.org/)

セッション: VR and Agents for Health

292
5 件の発表
2022-05-02 20:00:00
2022-05-02 21:15:00