Klasifikasi Analisis Sentimen Terhadap Kasus Penusukan Wiranto Media Sosial Twitter Dengan Menggunakan Metode Naïve Bayes Classification

Abstract

The existence of Twitter has been widely used by various levels of society in the last few years. The habit of the public to post tweets to assess the wiranto stabbing case is one of the media in representing the public's response to the stabbing case. Therefore, in this study, an analysis of public sentiment will be carried out on the case of Wiranto di stabbing which was revealed through the Twitter social network. The analysis was carried out by using the tweet classification which contains the public's sentiment regarding the Wiranto stabbing case. The classification method used in this study is the Naive Bayes Classification (NBC). NBC was used to obtain a classification of positive and negative responses to the public on Twitter and to obtain the preference value from the community for stabbing cases. The results of testing the percentage of wiranto data methods of 25%, 50%, 75%, and 100% of the amount of data from the training data resulted in an accuracy of 64.67%, 70.57%, 87.56%, 97.50. And for the results of testing the positive response of the community on Twitter with a preference value of 53%. Thus, sentiment classification using the Naive Bayes classification method can be used to measure the public response to the Wiranto stabbing case.

Keywords: Twitter, Naive Bayes, sentiment analysis.