Music Genre Classification Using Support Vector Machine Techniques

The classification of musical genres is crucial for enhancing music lovers' listening experiences, considering the vast amount of music available worldwide. This study conducted an in-depth analysis of a dataset obtained from Kaggle, which comprised detailed information on various music genres and their associated features. The dataset was grouped into four genres: pop, rap, rock, and hip-hop. To perform genre classification and compare the accuracy and F1 score, several machine learning algorithms, such as SVM Linear, SVM RBF, SVM Poly, and SVM Sigmoid, were employed. The team identified the most significant features that contributed to the classification process. The results of the study revealed that the SVM Linear algorithm outperformed other SVM kernels in regard to accuracy and F1 score. This finding indicates that SVM Linear is the most effective algorithm for classifying music genres in the dataset under investigation. The results of this study have important ramifications since they provide light on musical genre classification and the potential application of machine learning methods to improve genre identification precision. In addition, this study may have applications for music streaming services, recommendation engines, and other music-related software, providing users with a more personalized and enjoyable music listening experience.