Voice assistant guides users to understand personal sleep changes better
Guided Reflection for Personal Sleep Insight in Everyday Sleep Tracking
Human-Computer Interaction
Summary
Many people use digital tools to track their sleep, but they often find it hard to understand what changes in their sleep data really mean. The authors created DREAM, a voice assistant powered by a large language model, that talks with users about their sleep diaries and encourages them to think about what the changes in their sleep might mean. Over six weeks, people using DREAM felt they understood their sleep better and were more motivated to try new strategies. This approach helps people become active learners about their own sleep rather than just passively receiving general advice.
What this means in practice
- •For consumer health app developers: Integrate conversational AI to prompt users to actively interpret their sleep data for more personalized health insights.$Commercial implications: Enables creation of voice-driven sleep apps that improve user engagement and understanding, differentiating products in the wellness market.
- •For digital wellbeing coaches: Use voice assistants to guide clients through reflecting on their sleep patterns, improving motivation and tailored recommendations.
Authors
Bokyung Kim, Amama Mahmood, Honghao Zhao, Molly E. Atwood, Luis F. Buenaver, Ziang Xiao, Chien-Ming Huang
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.