Enhancing Response Quality by Children in Voice-based Sleep Diaries via AI-based Continuous Feedback

Shanshan Chen et al.

Digital sleep diaries are widely used in clinical practice and research to monitor children’s subjective sleep quality. A well-known limitation of survey methods is that children may not provide high-quality responses because they cannot or are not motivated to do so. We examine how to design “live”, continuous feedback in voice-based sleep diaries in order to enhance the quality of children’s responses. In a co-design workshop, we explored children’s preferences for different forms of feedback. We designed and compared experimentally symbolic (smiley), numeric, and no-feedback conditions, showing that both feedback types improved response quality across questions. Finally, an eight-day field study revealed that feedback resulted in higher and more consistent quality in self-report over time. Across these three studies, children valued playful and clear feedback, with preferences shifting depending on their cognitive needs. Our findings provide evidence that effective feedback must balance affective engagement and cognitive clarity and adapt to different contexts. We contribute empirically supported design insights for creating child-centered voice-based surveys that aim to enhance children’s adherence in independent self-report surveys. Our recommendations based on the study of sleep diaries can potentially be applied in other areas using voice-based surveys.