Comparison of Naïve Bayes Classifier and Support Vector Machine Methods for Sentiment Classification of Responses to Bullying Cases on Twitter

Abstract

The rapid dissemination of information related to the K-Pop world, facilitated by social media, has made it easier to follow developments and controversies. One notable case that sparked extensive discussion on Twitter was the bullying allegations against Kim Garam of LE SSERAFIM. Researchers, using Twitter data, sought to analyze Indonesian public sentiment regarding this case through sentiment analysis, which classifies opinions as positive or negative. For processing textual data, text mining methods, particularly classification techniques, are employed. Two popular algorithms in text mining are the Naive Bayes classifier and the support vector machine (SVM). The Naive Bayes classifier is favored for its speed, simplicity, and high accuracy, while the SVM excels at identifying a hyperplane that maximizes the margin between classes. In this study, sentiment classification results were labeled as either positive or negative. The comparison between the Naive Bayes classifier and SVM for classifying responses to Kim Garam's bullying case on Twitter showed high accuracy rates: 93% for Naive Bayes and 97% for SVM. The higher accuracy of the SVM algorithm indicates its superiority over the Naive Bayes classifier in this context.