Exploring Expert Perspectives on Wearable-Triggered LLM Conversational Support for Daily Stress Management
2026-04-06 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created EmBot, a mobile app that uses signals from wearable devices to detect stress and then offers conversations powered by large language models to help manage that stress. They talked to 15 mental health experts using EmBot to learn what works well and what challenges appear when linking stress detection with chat support. Their study reveals important design ideas and issues for making stress-management apps that combine these technologies. This helps guide future tools aiming to support mental health through daily conversations triggered by real-time stress signals.
wearable devicesstress detectionlarge language modelsconversational AImental health supportdesign probesemi-structured interviewsstress managementmobile applicationshuman-computer interaction
Authors
Poorvesh Dongre, Sameer Neupane, Priyanka Jadhav, Nikitha Donekal Chandrashekar, Christian Webb, Denis Gračanin
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.