Better Adherence, Richer Context: A Field Evaluation of LLM-Powered Conversational Voice Diaries for Sleep

2026-06-16

AI Summary

Traditional sleep diaries suffer from low user adherence and lack contextual details about nocturnal sleep. This study introduces, for the first time, a large language model (LLM)-driven conversational voice interface for longitudinal sleep self-reporting, implemented via smart speakers to administer morning and evening voice diaries. The system integrates proactive prompts, structured dialogue flows, and adaptive follow-up questioning to collect rich, contextualized data. Results demonstrate significantly improved user adherence and enhanced capture of situational information, albeit with a modest reduction in completeness for certain structured fields. These findings highlight a critical trade-off between expressive richness and structural precision, offering a novel paradigm for designing naturalistic interactions in digital health applications.

Abstract

Sleep diaries are central to behavioral sleep medicine and cognitive behavioral therapy for insomnia, yet daily completion is difficult to sustain, and static forms often provide limited context for interpreting night-to-night sleep variation. We designed an LLM-powered conversational voice diary that delivers clinically grounded morning and evening sleep diary questions through proactive smart-speaker prompts, structured conversational intake, and adaptive follow-up dialogue. We evaluated the system in a four-week between-subjects field study with 30 university students, comparing it with a text-based mobile diary using matched diary items, reporting windows, and reminder intervals. Compared with the text-based diary, the conversational voice diary showed higher adherence and elicited more detailed contextual self-report about routines, stressors, environmental conditions, and other sleep-related factors. Participants also described the voice diary as easier to integrate into daily routines, despite longer perceived completion time. However, voice-based conversational intake produced lower completeness for some structured diary fields, revealing a trade-off between expressive richness and structured precision. These findings show both the promise and the challenge of using LLM-powered conversational voice assistants for longitudinal health self-report.

Problem

• sleep diaries
• adherence
• contextual self-report
• longitudinal health self-report
• behavioral sleep medicine

Innovation

• LLM-powered conversational agent
• voice diary
• sleep self-report
• adherence
• contextual richness