https://github.com/tanyakuznetsova/music_mental_health

Harnessing music's power for better mental health: genre recommendations and data-driven analysis of listeners' trends
https://github.com/tanyakuznetsova/music_mental_health

data-visualization decision-tree decision-tree-classifier exploratory-data-analysis k-means-clustering pca-analysis recommendation-system recommender-system surprise-python

Last synced: 2 days ago
JSON representation

Harnessing music's power for better mental health: genre recommendations and data-driven analysis of listeners' trends

• Host: GitHub
• URL: https://github.com/tanyakuznetsova/music_mental_health
• Owner: tanyakuznetsova
• Created: 2024-02-24T11:07:19.000Z (9 months ago)
• Default Branch: main
• Last Pushed: 2024-03-16T20:13:41.000Z (8 months ago)
• Last Synced: 2024-03-17T03:34:49.581Z (8 months ago)
• Topics: data-visualization, decision-tree, decision-tree-classifier, exploratory-data-analysis, k-means-clustering, pca-analysis, recommendation-system, recommender-system, surprise-python
• Language: Jupyter Notebook
• Homepage:
• Size: 3.27 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Music And Mental Health

Harnessing music's power for better mental health: genre recommendations and data-driven analysis of listeners' trends

In this project we explore the profound relationship between music and mental health through data analysis and machine learning techniques. Our goal is to uncover insights that promote well-being and offer personalized recommendations for better mental health outcomes.

### Exploratory Data Analysis (EDA)

In the EDA section, we delve deep into the dataset, examining various aspects of music and mental health. Through visualization and statistical analysis, we gain valuable insights into the correlation between music genres, listening habits, and mental well-being indicators.

### Recommender System

Our recommender system is designed to curate personalized genre recommendations tailored to individual mental health needs. By leveraging machine learning algorithms and user preferences, we offer genre recommendations that aim to improve listeners' mental well-being.

### Decision Tree Classifier

The Decision Tree classifier predicts the effect of music on mental health outcomes, categorizing the listeners by the effects that listening to music had on their mental health: whether it improved, worsened, or there was no effect. This model provides valuable insights into the potential therapeutic impact of different music genres on mental well-being. Using SelectKBest with ANOVA F-value scoring function to select the top K features that are most relevant to predicting the target variable. In context, this means selecting the top three features that are most relevant to predicting whether music improved, worsened, or did not affect a user's mental health. 

### Listener Segmentation

Using Principal Component Analysis (PCA) and k-means clustering, we segment listeners into distinct groups based on their music preferences and mental health indicators. This analysis enables us to identify patterns and trends among listeners, facilitating targeted interventions and personalized recommendations.