Cyberbullying in Text Content Detection: An Analytical Review

TL;DR

This systematic review analyzes cyberbullying detection in text on online social networks from 2017 to 2022. It maps forms and roles of cyberbullying, consolidates methodological approaches (primarily ML and DL) for text detection, and discusses dataset scarcity and multilingual challenges. The study also links cyberbullying detection to broader cybercrime literature and examines the legislative landscape across continents, highlighting data and policy gaps. Overall, the work underscores the dominance of data-driven methods while calling for richer, multilingual datasets and harmonized legal frameworks to advance practical detection and mitigation.

Abstract

Technological advancements have resulted in an exponential increase in the use of online social networks (OSNs) worldwide. While online social networks provide a great communication medium, they also increase the user's exposure to life-threatening situations such as suicide, eating disorder, cybercrime, compulsive behavior, anxiety, and depression. To tackle the issue of cyberbullying, most existing literature focuses on developing approaches to identifying factors and understanding the textual factors associated with cyberbullying. While most of these approaches have brought great success in cyberbullying research, data availability needed to develop model detection remains a challenge in the research space. This paper conducts a comprehensive literature review to provide an understanding of cyberbullying detection.

Figures (1)

• Figure 1: A real example of cyberbulling tweet captured from the social media site Twitter. Some parts of the image are blured to hide the identity of persons who are involved in the cyberbulling case makafui_2022.