IMPLEMENTASI ALGORITMA TF-IDF DAN SUPPORT VECTOR MACHINE TERHADAP ANALISIS PENDETEKSI KOMENTAR CYBERBULLYING DI MEDIA SOSIAL TIKTOK

Cyberbullying is the act of sending text, images, or videos using internet, mobile phones, other devices with aim hurting and shaming people. often done through several social media platforms, one which comments on TikTok application. According to a report by We Are Social, has 1.4 billion monthly active users aged 18 above globally. Indonesia currently ranks second in world terms users. As result, potential for cyberbullying instances will grow as number grows. By data mining, public can create detection system, perform analysis The method used Term Frequency-Inverse Document Frequency (TF-IDF) Support Vector Machine (SVM). stages passed are collect that labelled manually. Then, text preprocessing, tokenizing, weighting were carried out TF-IDF. implement algorithm detect comments. This study uses 80% training 20% testing data. From performance results algorithm, 88% overall accuracy, precision, 96% recall, 92% f1-score obtained detecting TikTok.