Detection of Cyberbullying in Social Networks Using Machine Learning Methods

Abstract

Increasing Internet use and facilitating access to online communities such as social media have led to the emergence of cybercrime. Cyber bullying, a new form of bullying that emerged recently with the development of social networks, means sending messages that include slanderous statements, or verbally bullying other people or persons in front of the rest of the online community. The characteristics of online social networks enable cyberbullies to access places and countries that were previously unattainable. In this study; the use of natural language processing techniques and machine learning methods namely, Bayesian logistic regression, random forest algorithm, multilayer sensor, J48 algorithm and support vector machines have been used to determine cyber bullying. To the best of our knowledge, the successes of these algorithms with different metrics within different experiments have been compared for the first time to the real data.