The folder structure for this repository is as follows:
- Exploration: Contains code for initial exploratory analysis
- Cassandra_MLlib: Contains code for the initial load and pre-processing of the dataset in Cassandra and MLlib analysis of the data
- Sentiment_Lexical: Contains code for analysis of the lyrics in terms of sentiment and lexical diversity
- Clustering: Contains code for the clustering analysis
- Visualization: Contains added visualizations that were not included in the paper