Cyberbullying Detection Through Sentiment Analysis

Abstract

In recent years with the widespread of social media platforms across the globe especially among young people, cyberbullying and aggression have become a serious and annoying problem that communities must deal with. Such platforms provide various ways for bullies to attack and threaten others in their communities. Various techniques and methodologies have been used or proposed to combat cyberbullying through early detection and alerts to discover and/or protect victims from such attacks. Machine learning (ML) techniques have been widely used to detect some language patterns that are exploited by bullies to attack their victims. Also. Sentiment Analysis (SA) of social media content has become one of the growing areas of research in machine learning. SA provides the ability to detect cyberbullying in real-time. SA provides the ability to detect cyberbullying in real-time. This paper proposes a SA model for identifying cyberbullying texts in Twitter social media. Support Vector Machines (SVM) and Naïve Bayes (NB) are used in this model as supervised machine learning classification tools. The results of the experiments conducted on this model showed encouraging outcomes when a higher n-grams language model is applied on such texts in comparison with similar previous research. Also, the results showed that SVM classifiers have better performance measures than NB classifiers on such tweets.