GaMuSo: Graph Base Music Recommendation in a Social Bookmarking Service

In this work we describe a recommendation system based upon user-generated description (tags) of content. In particular, we describe an experimental system (GaMuSo) that consists of more than 140.000 user-defined tags for over 400.000 artists. From this data we constructed a bipartite graph, linking artists via tags to other artists. On the resulting graph we compute related artists for an initial artist of interest. In this work we describe and analyse our system and show that a straightforward recommendation approach leads to related concepts that are overly general, that is, concepts that are related to almost every other concept in the graph. Additionally, we describe a method to provide functional hypothesis for recommendations, given the user insight why concepts are related. GaMuSo is implemented as a webservice and available at: music.biograph.be.