A method for categorizing streamed music based on a sample set of RTP scores for predetermined tracks. High-level acoustic attributes for tracks are determined by an analyzed extraction of low-level data from the tracks. The high-level acoustic attributes are used to develop computer-derived RTP scores for the tracks based on the sample set, which includes RTPs score for a plurality of possible combinations of a rhythm score (R), a texture score (T), and a pitch score (P) respectively from a R range, a T range, and a P range. At least some of the RTP scores correspond to human-determined RTP scores for predetermined tracks among a plurality of predetermined tracks. Each RTP score corresponds to a category among a plurality of categories. The computer-derived RTP scores are used to determine a category for each track among the plurality of categories. Playlists of the tracks are based on one or more of the categories.