Graph Theory Exploration of Genre Interdependencies in Music Genres

Abstract

This study uses graph theory to investigate the complex relationships between musical genres in a dataset of Spotify tracks. A novel approach was used to create an adjacency matrix in which each node represents a genre and the edges reflect the interdependence of musical metrics. Popularity, duration, danceability, energy, key, loudness, mode, speechiness, acousticness, instrumentalness, liveness, valence, tempo, and time signature are all weighted metrics. This method reveals genre connections using statistical relationships, resulting in a structured framework for understanding genre dynamics. This method helps uncover hidden structures in music data by looking at how specific features influence genre classification. The findings show that graph theory has the potential to uncover underlying patterns and relationships that can be used in music recommendation systems, genre prediction algorithms, and other music information retrieval research.