π€ AI Summary
This study explores the effective integration of stress events detected by wearable devices with large language model (LLM)-driven conversational support for everyday stress management. To this end, we developed EmBot, a mobile application that combines real-time physiological signal triggering with generative dialogue. Through semi-structured interviews with 15 mental health professionals, we systematically analyzed the design considerations and key tensions inherent in this integration. As the first work to investigate, from a design perspective, the synergy between wearable-triggered interventions and LLM-powered conversations in mental health support, this research proposes a novel paradigm for daily stress intervention and distills core design principles and practical recommendations to inform the development of future intelligent mental health systems.
π Abstract
Wearable devices increasingly support stress detection, while LLMs enable conversational mental health support. However, designing systems that meaningfully connect wearable-triggered stress events with generative dialogue remains underexplored, particularly from a design perspective. We present EmBot, a functional mobile application that combines wearable-triggered stress detection with LLM-based conversational support for daily stress management. We used EmBot as a design probe in semi-structured interviews with 15 mental health experts to examine their perspectives and surface early design tensions and considerations that arise from wearable-triggered conversational support, informing the future design of such systems for daily stress management and mental health support.