A Multi-Modal AI Framework for Emotion-Aware Music Recommendation and Mental Health Signal Detection through User Listening Behaviour

Ramachandran, Hariramakrrishnan (2025) A Multi-Modal AI Framework for Emotion-Aware Music Recommendation and Mental Health Signal Detection through User Listening Behaviour. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (2MB) | Preview

Abstract

The study demonstrates a multi-modal AI system of emotion-aware music suggestion and mental health signal recognition that incorporates acoustic, lyrical and behavioral aspects of user engagement. The system consists of machine and deep learning technologies to identify audio characteristics, the mood of the lyrics and the user listening history, and can make suggestions that are adaptive to the emotional context. A sequential LSTM model represents behavioral drift, whereas a fusion layer integrates multi modular information into an understandable decision-making process. SHAP and gradient-based analysis are explainable AI techniques that can be used to improve the transparency and trust of the model. The construct illustrates the way user behavior modelling and emotion recognition can be used together to inform intelligent context-sensitive music systems. In addition to personalization, the paper addresses the possibility to connect emotion-aware recommendation with signs of mental health, which also leads to the creation of empathetic, morally responsible, and user-oriented AI in online music services.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Basilio, Jorge UNSPECIFIED
Subjects:	Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence B Philosophy. Psychology. Religion > Psychology > Emotions R Medicine > RA Public aspects of medicine > RA790 Mental Health H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Music Industry
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	08 Sep 2026 11:43
Last Modified:	08 Sep 2026 11:43
URI:	https://norma.ncirl.ie/id/eprint/9896

Actions (login required)

View Item