Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Xingbo, Griffith, Janessa, Adler, Daniel A., Castillo, Joey, Choudhury, Tanzeem, Wang, Fei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916880507207680
author Wang, Xingbo
Griffith, Janessa
Adler, Daniel A.
Castillo, Joey
Choudhury, Tanzeem
Wang, Fei
author_facet Wang, Xingbo
Griffith, Janessa
Adler, Daniel A.
Castillo, Joey
Choudhury, Tanzeem
Wang, Fei
contents Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.
format Preprint
id arxiv_https___arxiv_org_abs_2502_13920
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health
Wang, Xingbo
Griffith, Janessa
Adler, Daniel A.
Castillo, Joey
Choudhury, Tanzeem
Wang, Fei
Human-Computer Interaction
Computation and Language
Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.
title Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health
topic Human-Computer Interaction
Computation and Language
url https://arxiv.org/abs/2502.13920