A Robust Hybrid Machine Learning based Implications and Preventions of Social Media Blackmailing and Cyber bullying: A Systematic Approach

Abstract

In this contemporary era, the internet has become the mode of communication and has changed the lifestyle of individuals with advancements in technology. Social media networks are becoming an essential part of life for most of the world’s population. Social
 networking platforms give users countless opportunities to share information collaborate, cyberbullying and communicate positively. Cyberbullying is the use of technology as a medium to bully someone. Although it has been an issue for many years, the recognition of its impact on young people has recently increased. Detecting cyberbullying using Machine learning and natural language processing algorithms is getting the attention of researchers. The same platform can be extended to a fabricated and poisonous atmosphere that gives an impersonal, harmful platform for online misuse and assault. Yet it also poses significant challenges, including blackmailing and cyberbullying. These malicious activities can have severe psychological, emotional, and social consequences.  These unsolicited activities have an impact on increasing the vulnerability of crime against women and among younger age groups children including adolescents. This paper provides a comprehensive analysis of the phenomenon of social media blackmailing and cyberbullying. It examines their prevalence, psychological impacts, and countermeasures. The framework considering all possible actors in the cyberbullying event must be designed, including various aspects of cyberbullying and its effect on the participating actors. A synthesis of findings from recent studies is presented to highlight the trends and effectiveness of current mitigation strategies. The paper also outlines methodologies employed in recent research, discusses results, and provides conclusions on future directions. Furthermore, Future developments of the work could include handling multimedia data of various sizes and the ability to categorize the material neural network-based algorithms and future challenges are also discussed.