Problem
Research questions and friction points this paper is trying to address.
sleep tracking
guided reflection
personal sleep insight
behavioral sleep medicine
data interpretation
Guided Reflection for Personal Sleep Insight in Everyday Sleep Tracking
🤖 AI Summary
This study addresses the challenge users face in interpreting sleep monitoring data by proposing DREAM, a large language model-based voice assistant. The work innovatively integrates the concept of guided discovery from behavioral sleep medicine into daily tracking. Through conversational sleep diaries and voice interaction technologies, DREAM externalizes experts' tacit judgments and supports personalized interpretation of sleep changes via guided reflection. Empirical results demonstrate that DREAM significantly enhances users' personal insight, motivation, and intention for continued use, facilitating their transition from passive data recipients to active interpreters of their sleep. This research establishes a novel paradigm for AI-driven personalized sleep health management.
📝 Abstract
Digital sleep technologies make tracking accessible, yet users often struggle to interpret what changes in their sleep mean. Behavioral sleep medicine addresses this through guided discovery, helping patients develop personal interpretations rather than simply receiving explanations. To bring this to everyday tracking, we present DREAM, an LLM-powered voice assistant that monitors conversational sleep diaries, selectively invites users to interpret meaningful changes, and uses their interpretation to tailor subsequent education. We co-designed DREAM with sleep specialists iteratively and evaluated it in a six-week field study (N=14) against a generic-education control. DREAM participants reported greater personal sleep insight, motivation, and willingness to use the system, and described a clearer rationale for trying strategies. Our findings suggest that guided reflection made participants more active interpreters of their own sleep. Furthermore, we argue that expert involvement is not a single transfer of knowledge but an ongoing process of making tacit judgment explicit and testable.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Large Language Model
Guided Reflection
Voice Assistant
Sleep Tracking
Personalized Education
🔎 Similar Papers
No similar papers found.
