Perbandingan Kinerja Algoritma K-Nearest Neighbor, Naïve Bayes Classifier dan Support Vector Machine dalam Klasifikasi Tingkah Laku Bully pada Aplikasi Whatsapp

Abstract

WhatsApp is the most popular messaging application in Indonesia. This causes the emergence of cyberbullying behavior by its users. This study aims to classify WhatsApp chat to two classes, namely bully and not bully. The classification algorithms used are k-NN, NBC and SVM. The results show that the SVM algorithm is better at solving this case with an accuracy of 81.58%.