Cyberbullying comment classification on Indonesian Selebgram using support vector machine method

Abstract

This paper aims to classify comments containing cyberbullying on instagram social media. Data were taken from the comments on instagram accounts of some well-known Indonesian Instagram celebrities/Selebgram, 1053 comments were taken as a training document and 34 comments were taken as a test document. Text classification method used is Support Vector Machine (SVM). The Support Vector Machine (SVM) method is used for classification types that only have two values, namely −1 and 1. In this classification process, the Support Vector Machine (SVM) method is used to see how far this method can classify comments on the Indonesian account Contains cyberbullying or not. The language used to create a text classification program with Support Vector Machine (SVM) is the R language using RStudio's Integrated Development Environment (IDE). The result shows that the classification of cyberbullying comments on instagram account of Indonesian program using Support Vector Machine (SVM) method shows the result of accuracy percentage of 79, 412%.