Evaluating Text Features for Lyrics-Based Songwriter Prediction

Abstract

We offer an automated way of estimating the author of a song using only its lyrics content. To this end, we introduce a complete text classification framework which takes raw lyrics data as input and report estimated songwriter. The performance of the system is evaluated based on its classification and retrieval ability on a large dataset of Turkish songs, which was collected in this study. The results promote the use of such technique as a complementary tool in music information retrieval applications.