A Biofeedback-Driven Interaction System for Real-Time Stress Detection and Intervention

Abstract

This paper presents a novel prototype for a biofeedback system that uses real-time physiological data to detect task-related stress during everyday computer use, with electrodermal activity (EDA) and photoplethysmography (PPG) sensors directly integrated into a computer mouse. By continuously monitoring stress levels with this data, the system enables immediate, adaptive responses to elevated stress levels, aimed at reducing cognitive load. These responses take the form of on-screen, evidence-based mental health exercises designed to enhance user well-being. The interventions, drawn from Cognitive Behavioral Therapy (CBT) and Dialectical Behavioral Therapy (DBT), are delivered through context-aware, discreet pop-up windows that gently prompt users toward stress-reduction behaviors. An exploratory user study found that participants responded positively to the system’s ease of use, its ability to deliver timely support, and its potential to simplify self-directed mental health care through non-intrusive measures. Early findings point to strong user receptivity and validate the concept of embedding stress-responsive interventions into routine computing workflows. While further development is needed to improve personalization, comfort, and model accuracy, this work offers a compelling foundation for future systems that aim to deliver accessible, low-effort mental health support in real time.

Keywords: Affective Computing, Human-Computer Interaction, Biofeedback, Physiological Sensing, Stress Detection

DOI: 10.54941/ahfe1006725