Predicting Music Sentiment: A Comparative Analysis of Machine Learning Models Before and After Feature Selection
This study delves into the intersection of music and machine learning, examining the performance of five algorithms—Logistic Regression, Random Forest, Decision Tree, Support Vector Machine, and K-Nearest Neighbours—in sentiment analysis for music. The goal is to systematically evaluate their effectiveness in decoding and classifying the emotional content of musical compositions. The selected algorithms represent diverse computational approaches, contributing to the overarching objective of understanding the intricate emotional landscape of music. A crucial aspect of this comparative analysis involves assessing the accuracy of these machine learning models, both before and after applying feature selection techniques. This step proves critical in enhancing the predictive capabilities of the models. The observed accuracy levels exhibit a dynamic range from 57% to 67%, unveiling subtle yet noteworthy performance variations among the chosen algorithms.