Abstract
The classification of music genres has been studied using various auditory, linguistic, and metadata features. Classification using linguistic features typically results in lower accuracy than classifiers built with auditory features. In this paper, we hand-craft features unused in previous lyrical classifiers such as rhyme density, readability, and the occurrence of profanity. We use these features to train traditional machine learning models for lyrical classification across nine popular music genres and compare their performance. The features that contribute the most towards this classification problem, and the genres that are easiest to predict, are identified. The experiments are conducted on a set of over 20,000 lyrics. A final accuracy of 56.14% was achieved when predicting across the nine genres, improving upon accuracies obtained in previous studies.
Highlights
Classifying music is imperative for online music streaming services such as Spotify, YouTube Music and iTunes, as it allows them to provide a rich user experience – for example, Spotify provides automated playlists for over 5000 genres of music (Rodgers, 2020)
Music genres are a popular method for categorisation in computer applications – genres are typically defined by characteristics such as tempo, instruments, vocalisations, rhythmic structure, lyrical style (KOOP, 2019)
The feature importance for two models created in this paper can be seen in Figure 5 – since the models were fit using the principal components analysis (PCA) components, the importances are in terms of these components
Summary
Classifying music is imperative for online music streaming services such as Spotify, YouTube Music and iTunes, as it allows them to provide a rich user experience – for example, Spotify provides automated playlists for over 5000 genres of music (Rodgers, 2020). Being able to automatically classify music into different genres is beneficial to these streaming services as it reduces the time and effort required by record label or streaming service employees to correctly categorise music. This is one reason why the classification of music audio and lyrics into genres has been well-researched (Fell and Sporleder, 2014; Tzanetakis and Cook, 2002; Zhang et al, 2016). Classification using lyrics has not been able to predict the music genre of songs as accurately as that of audio classifiers (Silla Jr. et al, 2008)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Reinvention: an International Journal of Undergraduate Research
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
