Mobile Music Therapy Integrating AI-Driven Emotion Prediction and a Human-Computer Interaction Experience Model.

Saved in:

Bibliographic Details
Title:	Mobile Music Therapy Integrating AI-Driven Emotion Prediction and a Human-Computer Interaction Experience Model.
Authors:	Bai, Ruqi¹ 18603502125@163.com
Source:	International Journal of Interactive Mobile Technologies. 2026, Vol. 20 Issue 3, p55-70. 16p.
Subjects:	Music therapy, Affective computing, Human-computer interaction, Emotion regulation, Multisensor data fusion, Deep learning, Medical care, Affective forecasting (Psychology)
Abstract:	The integration of affective computing with mobile health technologies has created transformative opportunities for scalable and personalized music therapy. However, traditional music therapy remains limited by insufficient personalization, subjective emotion assessment, and low adaptability in human--computer interaction (HCI). Existing artifi- cial intelligence (AI) emotion prediction methods also lack robust multimodal data fusion in mobile environments and alignment with clinical workflows. A closed-loop mobile music therapy system incorporating multimodal AI emotion prediction was developed in this study to address these limitations. The system integrates multimodal emotion sensing, dynamic therapy matching, empathic interaction, and closed-loop optimization. A convolutional neural network-long short-term memory (CNN-LSTM) hybrid model was employed to predict emotional states using physiological signals, behavioral features, and subjective feedback, while a prescriptive dynamic music therapy model and a multidimensional HCI evaluation framework were constructed. Experimental results showed that the multimodal CNN--LSTM model outperformed unimodal models and traditional algorithms, and the closed-loop system achieved significantly greater improvements in emotional regulation and stress reduction than non-adaptive interventions (traditional therapy approaches and static playlists). Dynamic enhancements in heart rate variability and reductions in cortisol levels provided objective physiological evidence of therapeutic efficacy. The empathic interaction framework increased usability and treatment adherence. Mediation analysis confirmed the pathway linking emotion prediction, music therapy matching, and outcome enhancement. Superior efficacy in individuals with anxiety or depressive tendencies further highlighted scenario-specific therapeutic responsiveness compared with postoperative rehabilitation groups. This study advances the integration of AI and music therapy, and the proposed real-time mapping model linking emotional states, music parameters, and interaction feedback provides an actionable framework for the development of empathic AI systems in healthcare. The closed-loop design establishes a new paradigm for personalized mobile medical interventions with significant clinical and interdisciplinary relevance. [ABSTRACT FROM AUTHOR]
	Copyright of International Journal of Interactive Mobile Technologies is the property of International Journal of Interactive Mobile Technologies and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The integration of affective computing with mobile health technologies has created transformative opportunities for scalable and personalized music therapy. However, traditional music therapy remains limited by insufficient personalization, subjective emotion assessment, and low adaptability in human--computer interaction (HCI). Existing artifi- cial intelligence (AI) emotion prediction methods also lack robust multimodal data fusion in mobile environments and alignment with clinical workflows. A closed-loop mobile music therapy system incorporating multimodal AI emotion prediction was developed in this study to address these limitations. The system integrates multimodal emotion sensing, dynamic therapy matching, empathic interaction, and closed-loop optimization. A convolutional neural network-long short-term memory (CNN-LSTM) hybrid model was employed to predict emotional states using physiological signals, behavioral features, and subjective feedback, while a prescriptive dynamic music therapy model and a multidimensional HCI evaluation framework were constructed. Experimental results showed that the multimodal CNN--LSTM model outperformed unimodal models and traditional algorithms, and the closed-loop system achieved significantly greater improvements in emotional regulation and stress reduction than non-adaptive interventions (traditional therapy approaches and static playlists). Dynamic enhancements in heart rate variability and reductions in cortisol levels provided objective physiological evidence of therapeutic efficacy. The empathic interaction framework increased usability and treatment adherence. Mediation analysis confirmed the pathway linking emotion prediction, music therapy matching, and outcome enhancement. Superior efficacy in individuals with anxiety or depressive tendencies further highlighted scenario-specific therapeutic responsiveness compared with postoperative rehabilitation groups. This study advances the integration of AI and music therapy, and the proposed real-time mapping model linking emotional states, music parameters, and interaction feedback provides an actionable framework for the development of empathic AI systems in healthcare. The closed-loop design establishes a new paradigm for personalized mobile medical interventions with significant clinical and interdisciplinary relevance. [ABSTRACT FROM AUTHOR]
ISSN:	18657923
DOI:	10.3991/ijim.v20i03.60249