Review on Detection of Cyberbullying using Machine Learning
Shivam Kushwaha, Apoorva Mhalas, Rutik Thakur, Vikrant Gujrathi, Swati Khokale · Journal of Emerging Technologies and Innovative Research · 2021
Abstract-Internet has touched every aspect of human life, bringing ease in connecting people around the globe and has made information available to huge strata of society with a click of a button. With advancement, came unforeseen banes of cyber offences. Cyberbullying is a form of electronic communication, which harms the reputation or privacy of an individual, or threatens, or harasses, leaving a long-lasting impact. Although it has been an issue for many years, the recognition of its impact on young people has recently increased. Through machine learning, we can detect language patterns used by bullies and their victims, and develop rules to automatically detect cyberbullying content. We comprehensively review cyberbullying prediction models and identify the main issues related to the construction of cyberbullying prediction models. This paper provides insights on the overall process for cyberbullying detection and most importantly overviews the methodology. Through data collection and feature engineering process has been elaborated, yet most of the emphasis is on feature selection algorithms and then using various machine-learning algorithms for prediction of cyberbullying behaviours. A supervised Learning Algorithm, which gives the highest accuracy, was used for the detection of cyberbullying activity over the internet.