INDONESIAN LANGUAGE CLASSIFICATION OF CYBERBULLING WORDS ON TWITTER USING ADABOOST AND NEURAL NETWORK METHODS

Cyberbullying is a very interesting research topic because of the development of communication technology, especially social media, which causes negative consequences where people can bully each other, causing victims and even suicide. The phenomenon of Cyberbullying detection has been widely researched using various approaches. In this study, the AdaBoost and Neural Network methods were used, which are machine learning methods in classifying Cyberbullying words from various comments taken from Twitter. Testing the classification results with these two methods produces an accuracy rate of 99.5% with Adaboost and 99.8% using the Neural Network method. Meanwhile, when compared to other methods, the results obtained an accuracy of 99.8% with SVM and Decision Tree, 99.5% with Random Forest. Based on the research results of the Neural Network method, SVM and Decision Tree are tested methods in detecting the word cyberbullying proven by achieving the highest level of accuracy in this study

Abstract licence: CC BY-NC

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.