GPTCoach: Towards LLM-Based Physical Activity Coaching

Abstract

Mobile health applications show promise for scalable physical activity promotion but are often insufficiently personalized. In contrast, health coaching offers highly personalized support but can be prohibitively expensive and inaccessible. This study draws inspiration from health coaching to explore how large language models (LLMs) might address personalization challenges in mobile health. We conduct formative interviews with 12 health professionals and 10 potential coaching recipients to develop design principles for an LLM-based health coach. We then built GPTCoach, a chatbot that implements the onboarding conversation from an evidence-based coaching program, uses conversational strategies from motivational interviewing, and incorporates wearable data to create personalized physical activity plans. In a lab study with 16 participants using three months of historical data, we find promising evidence that GPTCoach gathers rich qualitative information to offer personalized support, with users feeling comfortable sharing concerns. We conclude with implications for future research on LLM-based physical activity support.

Please note that the title has been updated from a previous pre-print (previously: "Supporting Physical Activity Behavior Change with LLM-Based Conversational Agents")

References in corpus (4)

• The Development and Validation of the Technology-Supported Reflection Inventory
• Evaluating the Experience of LGBTQ+ People Using Large Language Model Based Chatbots for Mental Health Support
• From Classification to Clinical Insights: Towards Analyzing and Reasoning About Mobile and Behavioral Health Data With Large Language Models
• Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform

Cited by in corpus (4)

• Laissez-Faire Harms: Algorithmic Biases in Generative Language Models
• SmartWalkCoach: An AI Companion for End-to-End Walking Guidance, Motivation, and Reflection
• Chaplains' Reflections on the Design and Usage of AI for Conversational Care
• Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving