Music is often used to influence moods, and with growing awareness around mental health, understanding the impact of listening habits on mental well-being is crucial. This project aims to analyze a dataset to identify patterns in listening habits that positively or negatively affect mental health. The insights gained could help individuals adjust their music consumption to improve their mental well-being.
This project explores the relationships between the listening habits of a diverse group of individuals and their reported mental health status using this Kaggle dataset. Exploratory Data Analysis (EDA) was performed to uncover these relationships, supported by visualizations. Additionally, a Random Forest Classification model was trained on the cleaned and formatted data. The model uses the most impactful features identified through feature importance analysis to predict whether certain personal features and listening habits can lead to improved mental health.
- Music_Mental_Analysis.ipynb: This Jupyter Notebook contains all data analysis, visualizations, and model training. It was developed for use in Google Colab.
- Music_MentalHealth_Data.csv: This is the dataset from Kaggle, which includes mental health information and personal details collected through a survey distributed across various online forums.