Although content is fundamental to our music listening preferences, the leading performance in music recommen-dation is achieved by collaborative-filtering-based methods which exploit the similarity patterns in user's listening his-tory rather than the audio content of songs. Meanwhile, collaborative filtering has the well-known " cold-start " prob-lem, i.e., it is unable to work with new songs that no one has listened to. Efforts on incorporating content informa-tion into collaborative filtering methods have shown suc-cess in many non-musical applications, such as scientific article recommendation. Inspired by the related work, we train a neural network on semantic tagging information as a content model and use it as a prior in a collaborative fil-tering model. Such a system still allows the user listening data to " speak for itself " . The proposed system is evalu-ated on the Million Song Dataset and shows comparably better result than the collaborative filtering approaches, in addition to the favorable performance in the cold-start case.
Mendeley saves you time finding and organizing research
Choose a citation style from the tabs below