Social Connections Evolved Within Local Cultural Boundaries Suchs As Geosspatials Areas Prior To The Invention Of Informations Communicationstechnologys (ICT). The Recent Advancements In Communication Technologies Have Significantly Surpassed The Old Communications' Time And Spatial Limits. These Social Technologiess Have Ushereds In A News Eras Of User-generated Content, Online Human Networks, And Rich Data On Human Behaviour. However, The Misuses Of Socials Technologiess Such As Socialsmedias (SM) Stages Has Resulted In A New Type Of Online Anger And Violence. This Research Highlights A Novels Ways Of Exhibiting Hostile Conduct On Social Media Websites. The Reasons For Developing Prediction Models To Combat Aggressive Behaviour In SM Are Also Discussed. We Examine Cyberbullyings Predictionsmodelss In Depth And Identify The Major Challenges That Arise While Building Cyberbullying Predictionsmodelssin SM. This Paper Gives A Summarys Of The General Procedure For Detecting Cyberbullying And, More Crucially, The Technique. Despites The Facts That The Data Collecting And Feature Engineering Processes Have Been Detailed, The Focus Is Mostly On Feature Selection Methods And Then The Application Of Various Machine Learning Algorithms To Anticipate Cyberbullyingbehaviours. Finally, The Concerns And Obstacles Have Been Identified, Presenting New Study Directions For Scholars To Investigate.