Using Song Social Tags and Topic Models to Describe and Compare Playlists

Playlists are a natural delivery method for music recommendation and discovery systems. Recommender systems offering playlists must strive to make them relevant and enjoyable. In this paper we survey many current means of generating and evaluating playlists. We present a means of comparing playlists in a reduced dimensional space through the use of aggregated tag clouds and topic models. To evaluate the fitness of this measure, we perform prototypical retrieval tasks on playlists taken from radio station logs gathered from Radio Paradise and Yes.com, using tags from Last.fm with the result showing better than random performance when using the query playlist's station as ground truth, while failing to do so when using time of day as ground truth. We then discuss possible applications for this measurement technique as well as ways it might be improved.