Towards Developing a Content-Based Recommendation System for Classical Music
Music recommender systems have become a popular tool utilized by numerous online music streaming apps like Spotify and Apple Music. Despite the prevalence of music recommenders, not many have created one particularly for classical music. Although listeners of classical music are not typically dominant, they still constitute as a significant target group for music recommender systems. Majority of the mainstream recommendation systems use collaborative filtering which help predict the users’ music preferences based on their past preferences and preferences of similar users. The use of this popular recommendation method is not ideal for less mainstream music such as classical music as it holds bias towards more popular items such as those belonging to the pop genre. Classical music will greatly benefit from the use of a content-based recommendation system that will analyze the music’s rhythmic, melodical, and chordal features as these features help define a users musical taste. As such, we present an approach for content-based recommendation using similarity of classical music using high-level musical features. The preliminary results demonstrate the feasibility of these features and techniques in creating a content-based recommender for classical music.
Cruz, A. F. T., & Coronel, A. D. (2019). Towards developing a content-based recommendation system for classical music. In K. J. Kim & H.-Y. Kim (Eds.), Information Science and Applications (pp. 451–462). Springer. https://doi.org/10.1007/978-981-15-1465-4_45