Collaboration-Aware Hit Song Analysis and Prediction

We propose tackling the Hit Song Prediction problem through a multimodal form with songs’ features fused together. Specifically, we describe songs from three feature modalities: music, artist and album. Initially, we identify collaboration profiles in a success-based musical network, unveiling how professional connections can significantly impact their success. Then, we use time series and the Granger Causality test for assessing whether there is a causal relationship between collaboration profiles and artists’ popularity. Finally, we model the Hit Song Prediction problem as two distinct tasks: classification and placement. The former is a classical binary classification model and directly applies our fusion strategies. The latter is a modeling approach that ranks a song relative to a given chart, predicts hit songs, and provides comparative popularity information of a set of songs. Furthermore, we emphasize collaboration artists’ profiles as important features when describing their songs. Overall, our empirical studies confirm the effectiveness of our method that fuses heterogeneous data for both tasks.