Classification of origin with feature selection and network construction for folk tunes

Abstract

We address the question to what extent origin of folk songs can be predicted, and construct a song similarity network. For this we use feature selection and train a random forest classifier on extracted melody n-grams and rhythm grams of songs from 7 different groups of origin, 80 from each. We use its importances to reduce the feature space dimension for the construction of an informative network, which we visualized in a interactive web application. These tools have vast application in large-scale exploration in digitized music databases and for specific questions in musicology.