{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/machine-learning-and-chord-based-feature","title":"Machine learning and chord based feature engineering for genre prediction in popular Brazilian music","arxiv_id":"1902.03283","date":"2019-02-08","proceeding":null,"authors":["Bruna D. Wundervald","Walmes M. Zeviani"],"abstract":"Music genre can be hard to describe: many factors are involved, such as\nstyle, music technique, and historical context. Some genres even have\noverlapping characteristics. Looking for a better understanding of how music\ngenres are related to musical harmonic structures, we gathered data about the\nmusic chords for thousands of popular Brazilian songs. Here, 'popular' does not\nonly refer to the genre named MPB (Brazilian Popular Music) but to nine\ndifferent genres that were considered particular to the Brazilian case. The\nmain goals of the present work are to extract and engineer harmonically related\nfeatures from chords data and to use it to classify popular Brazilian music\ngenres towards establishing a connection between harmonic relationships and\nBrazilian genres. We also emphasize the generalization of the method for\nobtaining the data, allowing for the replication and direct extension of this\nwork. Our final model is a combination of multiple classification trees, also\nknown as the random forest model. We found that features extracted from\nharmonic elements can satisfactorily predict music genre for the Brazilian\ncase, as well as features obtained from the Spotify API. The variables\nconsidered in this work also give an intuition about how they relate to the\ngenres.","url_abs":"http://arxiv.org/abs/1902.03283v1","url_pdf":"http://arxiv.org/pdf/1902.03283v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"machine-learning-and-chord-based-feature","repo_url":"https://github.com/brunaw/genre_classification","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"feature-engineering","task_name":"Feature Engineering"},{"task_slug":"music-genre-recognition","task_name":"Music Genre Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/music-genre-recognition-on-chords","task":"Music Genre Recognition","dataset":"chords","model":"random forest","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"62%"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}