Machine and Deep Learning Studies for Cyberbullying Detection

Abstract

The internet revolution in society has various effects on our daily life such as the use of social media. While social media is ubiquitous and great in some aspects, it brings a new issue that appears more and more in today’s world. This new issue, Cyberbullying, involves harming someone by posting or sharing content that causes feelings of embarrassment, guilt, or humiliation. Easily creating fake social media accounts with fake identity further increase cyberbullying incidents and encourages cyberbullies. Cyberbullying can affect people both mentally and physically and can lead to permanent problems. However, studies in this area show that cyberbullying can be prevented. In this study, we review machine learning techniques to detect and prevent cyberbullying, evaluate the performances of the machine and deep learning models, and examine factors that affect the performance of the models. We also discuss the importance of data preprocessing, feature extraction and selection, and classification processes in cyberbullying detection problems.