Music perception is highly intertwined with both emotions and context. Not surprisingly, many of the users' information seeking actions aim at retrieving music songs based on these perceptual dimensions -- moods and themes, expressing how people feel about a piece of music or which situations they associate it with.  In order to successfully support music retrieval along these dimensions, powerful methods are needed. Still, most existing approaches aiming at inferring some of the songs' latent characteristics focus on identifying musical genres.

In this paper we aim at bridging this gap between users' information needs and indexed music features by developing algorithms for classifying music songs by moods and themes. We extend  existing approaches by also considering the songs' thematical dimensions and by using social data from the Last.fm music portal, as support for the classification tasks. Our methods exploit both audio features and collaborative user annotations, fusing them to improve overall performance. Evaluation performed against the AllMusic.com ground-truth shows that both kinds of information are complementary and should be merged for enhanced classification accuracy.