Abstract—Over the last several years, music streaming services have come in handy in our lives. Apple Music, Spotify, and Google Play Music is one of the most commonly used music streaming services. There are a number of studies about music recommendation system, one of the functions in music streaming services. Most of studies about music recommendation system express music features using music information extracted from song components. The way to express music features and to come up recommendations out of music features varies. In this paper, we consider couple of approaches that reflect users music preference including music features and construct our music recommendation model through those approaches. Our proposed method is to recommend music with user preference vector, which has users music preference, referring to the idea of contents-based filtering.
Index Terms—Personalized recommendation, feature extraction, music representations, weighting, affinity discovery.
H. Shinohara and K. Mizuno are with Takushoku University, Hachioji, Tokyo 193-0985 Japan (e-mail: shinoharahiroto0@gmail.com, mizuno@cs.takushoku-u.ac.jp).
[PDF]
Cite:Hiroto Shinohara and Kazunori Mizuno, "Music Recommendation for Individual Music Preference," International Journal of Computer Theory and Engineering vol. 11, no. 2, pp. 35-38, 2019.
