Defending Against Digital Threats: Machine Learning Techniques for Cyber Persecution Detection
P. Chinnasamy, Ramesh Kumar Ayyasamy, Kesavan Krishnan, Vijay Kumar, Norazira Binti A Jalil, Ajmeera Kiran · 2024
Cyber persecution has become a widespread problem on the social media. It has resulted in omissions such as suicide and sadness. Content regulation on social media sites is becoming increasingly important. The following work employs natural language processing and Machine Learning techniques to construct a cyber harassment detection model utilizing data from cyberbullying, hate speech tweets from Twitter, and personal assaults from Wikipedia. The optimal approach is investigated by two feature extraction methods and six classifiers (SVM, Random Forest, XGBoost, MLP, and Logistic Regression). This study summarizes the general procedure for detecting cyberbullying and, more crucially, the technique. During experimentation, SVM, Random Forest, and Logistic Regression performed well with an average of 90%. Our model has been created to detect offensive comments on social media websites.