Automatic identification of cyberbullying is a problem that is gaining traction, especially in the Machine Learning areas. Not only is it complicated, but it has also become a pressing necessity, considering how social media has become an integral part of adolescents' lives and how serious the impacts of cyberbullying and online harassment can be, particularly among teenagers. This paper contains a systematic literature review of modern strategies, machine learning methods, and technical means for detecting cyberbullying and the aggressive command of an individual in the information space of the Internet. We undertake an in-depth review of 13 papers from four scientific databases. The article provides an overview of scientific literature to analyze the problem of cyberbullying detection from the point of view of machine learning and natural language processing. In this review, we consider a cyberbullying detection framework on social media platforms, which includes data collection, data processing, feature selection, feature extraction, and the application of machine learning to classify whether texts contain cyberbullying or not. This article seeks to guide future research on this topic toward a more consistent perspective with the phenomenon's description and depiction, allowing future solutions to be more practical and effective.

No abstract