Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Context-AI Tunes: Context-Aware AI-Generated Music for Stress Reduction

Xiaoyan Wei, Zebang Zhang, Zijian Yue, Hsiang-Ting Chen

TL;DR

This work introduces Context-AI Tune (CAT), a system that generates personalized, context-aware relaxing music by integrating environmental cues captured via camera and self-reported stress. Using a 2×2 within-subject design (AI vs NoAI; Busy Hub vs Quiet Library) with N=26 and the Visual Analog Scale for Stress (VAS-S), the authors show that AI-generated music adapting to context yields greater stress reduction than hand-picked relaxing tracks. CAT's architecture combines a visual-language prompt workflow (via a ChatGPT-based extractor) with Suno API music generation, logging, and analysis to enable real-time, adaptive therapy. The results support the potential of context-aware AI music for stress management and provide design implications for interactive, personalized wellbeing technologies.

Abstract

Music plays a critical role in emotional regulation and stress relief; however, individuals often need different types of music tailored to their unique stress levels or surrounding environment. Choosing the right music can be challenging due to the overwhelming number of options and the time-consuming trial-and-error process. To address this, we propose Context-AI Tune (CAT), a system that generates personalized music based on environmental inputs and the user's self-assessed stress level. A 2x2 within-subject experiment (N=26) was conducted with two independent variables: AI (AI, NoAI) and Environment (Busy Hub, Quiet Library). CAT's effectiveness in reducing stress was evaluated using the Visual Analog Scale for Stress (VAS-S). Results show that CAT is more effective than manually chosen music in reducing stress by adapting to user context.

Context-AI Tunes: Context-Aware AI-Generated Music for Stress Reduction

TL;DR

This work introduces Context-AI Tune (CAT), a system that generates personalized, context-aware relaxing music by integrating environmental cues captured via camera and self-reported stress. Using a 2×2 within-subject design (AI vs NoAI; Busy Hub vs Quiet Library) with N=26 and the Visual Analog Scale for Stress (VAS-S), the authors show that AI-generated music adapting to context yields greater stress reduction than hand-picked relaxing tracks. CAT's architecture combines a visual-language prompt workflow (via a ChatGPT-based extractor) with Suno API music generation, logging, and analysis to enable real-time, adaptive therapy. The results support the potential of context-aware AI music for stress management and provide design implications for interactive, personalized wellbeing technologies.

Abstract

Music plays a critical role in emotional regulation and stress relief; however, individuals often need different types of music tailored to their unique stress levels or surrounding environment. Choosing the right music can be challenging due to the overwhelming number of options and the time-consuming trial-and-error process. To address this, we propose Context-AI Tune (CAT), a system that generates personalized music based on environmental inputs and the user's self-assessed stress level. A 2x2 within-subject experiment (N=26) was conducted with two independent variables: AI (AI, NoAI) and Environment (Busy Hub, Quiet Library). CAT's effectiveness in reducing stress was evaluated using the Visual Analog Scale for Stress (VAS-S). Results show that CAT is more effective than manually chosen music in reducing stress by adapting to user context.
Paper Structure (23 sections, 5 figures, 1 table)

This paper contains 23 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Music Therapy in HCI Research
  4. Generative AI in Music production
  5. System Design
  6. Implementation
  7. Environmental Analysis
  8. Music Generation
  9. Data Logging and Analysis
  10. User Study
  11. Participants
  12. Experimental Setup
  13. Interview
  14. Result
  15. Result of VAS-S Score
  16. ...and 8 more sections

Figures (5)

  • Figure 1: Main components of CAT
  • Figure 2: System Workflow
  • Figure 3: Experimental session flow, repeated four times for each participant across two different days. The process includes VAS-S questionnaire, math tasks, and a post-hoc interview to assess stress and engagement levels
  • Figure 4: VAS-S Means by Condition (B-Hub vs Q-Lib, AI vs NoAI)
  • Figure 5: VAS-S Score Variation Analysis in Four Conditions