Utilizing Machine Learning to Identify Mental Health Issues Based on Music Genre Preferences

Mental health issues have been increasing worldwide, with a sharp rise in cases over the last 30 years. This shows the need for better ways to identify and address these problems. This study looks at how machine learning can help identify mental health conditions like anxiety, depression, insomnia, and OCD based on people’s music preferences. Survey data on favorite music genres and self-reported mental health were analyzed using machine learning methods, including Logistic Regression, Decision Trees, and Gradient Boosting. Logistic Regression and Gradient Boosting worked the best, predicting anxiety with $32 \%$ accuracy after selecting key features. However, issues like unbalanced data and limited relevance of the information made it harder to improve the results. These findings highlight the correlation between the two, suggesting that while music and mental health might be connected, music preferences alone cannot accurately reflect a person’s mental health condition, as causation does not work both ways.