A Comprehensive Study on Cyberbullying Detection Using Machine Learning Approach

Abstract

Cyberbullying is an action where a person or a group of persons uses social networking sites
on internet through smartphones, computers, and tablets to trouble, distress, hurt or harm
another person. Cyberbullying occurs by sending, posting or sharing offensive or harmful texts,
images or videos. It also involves activities such as sharing someone’s personal or private
information which causes feeling of awkwardness and shame, also humiliation. These actions are
unlawful. With the increasing adverse impact of cyberbullying on society, it is necessary to find
ways to detect this phenomenon. Automatically identifying bully words, emojis and audio/video
features from online social platforms, especially micro-blogging site such as Twitter and videosharing platform such as YouTube is an important research. This paper presents a collective and
structured study to reconnoiter and assimilate research done in the field of detection of
cyberbullying, also research gaps are illustrated in a legitimate manner. The study portrays a
comprehensive systematic literature review of strategies proposed in the field of text-based and
video-based cyberbullying. The survey relates to several machine learning methodologies and
online social networking datasets used in previous studies and scope for improvement in
detection of cyberbullying. This methodical analysis of the research work acts as an assistant for
the researchers to discover the significant and compelling characteristics of cyberbullying
detection techniques. Finally, issues and challenges in cyberbullying detection are
highlighted and discussed.