Classification of Emotions on Song Lyrics using Naïve Bayes Algorithm and Particle Swarm Optimization

A song is a unity of sound that contains a tone and lyrics. A song can contain a variety of emotions. Emotions in the song can arise because of the combination of lyrics and tones that create a beautiful sound and harmony. This research is about the emotional content of the song lyrics. This research began with collecting datasets in the form of song lyrics from kapanlagi.com, liriklaguindonesia.net, and liriklaguanak.com as a provider of song lyrics. Then preprocessing data consists of case folding, tokenizing, stop removal, and stemming. After that, the part of speech (POS) tagging process automatically labels the word in the text according to the word class. Labeling a word, whether it's a verb, adjective, or description, to be able to determine the song's emotional lyrics according to what we listen to takes the right method. The method used is the Naive Bayes Classifier and Particle Swarm Optimization methods, as methods used in performing text classification. In some studies, it was mentioned that the Naive Bayes Classifier method shows good results in the case of the classification of Indonesian text information, with an accuracy of 90%–96% using an inertia weight score of 1.0.