Rocking around the clock eight days a week: an exploration of temporal patterns of music listening

Music listening patterns can be influenced by contextual factors such as the activity a listener is involved in, the place one is located or physiological constants. As a consequence, musical listening choices might show some recurrent temporal patterns.

Here we address the hypothesis that for some listeners, the selection of artists and genres could show a preference for certain moments of the day or for certain days of the week. With the help of circular statistics we analyze playcounts from Last.fm and detect the existence of that kind of patterns. Once temporal preference is modeled for each listener, we test the robustness of that using the listener’s playcount from a posterior temporal period. We show that for certain users, artists and genres, temporal patterns of listening can be used to predict music listening selections with above-chance accuracy.

This finding could be exploited in music recommendation and playlist generation in order to provide user-specific music suggestions at the “right” moment.