Analysis of Cyberbullying Level using Support Vector Machine Method

Internet users in Indonesia is increasing every year. The increase caused by several factors, such as the increasingly even distribution of internet infrastructure Indonesia. has a positive impact facilitating communication between individuals, while negative intimidation to someone or known cyberbullying. Cyberbullying huge on mental health person, causing victim be angry, depressed, and anxious. This research aims measure level cyberbullying Twitter using TF-IDF Support Vector Machine. Classification this study classified into two classes, namely non-cyberbullying. data used were 3,344,782 tweets that resulted classification 34.59% non-cyberbullying 65.41%. best accuracy value obtained 85%.