ANALISIS SENTIMEN TWITTER TERHADAP CYBERBULLYING MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)

Along with increasing technological advances in this digital era, people often use social media to interact with each other, the presence of information technology has a great influence on human civilization. Information can spread widely in a short time thanks to technological advances, one form of which is the use of social media. However, this has an impact on cyberbullying, especially on social media Twitter, according to UNICEF U-Report 2021, as many as 45 percent of 2,777 young people aged 14-24 years have experienced cyberbullying. In this regard, sentiment analysis was carried out through Twitter social media to find out how classification classification the Support Vector Machine (SVM) algorithm measured the accuracy value using the Support Vector Machine algorithm on Twitter regarding cyberbullying. In this study, a classification of positive sentiment and negative sentiment was carried out. From 1000 data crawled after preprocessing to 998 data, there were 625 data in the positive class and 374 data in the negative class. Classification using the Support Vector Machine (SVM) algorithm gets an accuracy of 92% by testing at 80:20 proportion, namely 80% training data and 20% testing data.

Keywords: Sentiment Analysis, Support Vector Machine (SVM), Twitter, Cyberbullying