Improving Cyberbullying Detection Accuracy with Advanced Machine Learning Models

Cyberbullying poses a significant threat to individuals well-being in online environments, necessitating effective detection and prevention measures. In this study, Attack detection across different online platforms involves conducting a comprehensive literature review to survey existing research efforts and highlight the diverse feature the different scope of machine learning procedures employed in this domain. Specifically, exploring utilization of Naive Bayes, Logistic Regression, Support Vector Machine (SVM), Neural Network (NN), Gradient Boosting Machine (GBM), Random Forest (RF), Decision Tree (DT) for cyber bullying detection. Each approach is evaluated based on its performance in identifying instances of cyberbullying behavior, leveraging textual, multimedia, and social network features. The Findings reveal the limitations and strength of various machine learning methods and offer perceptions into their applicability and effectiveness in addressing the complex challenges of cyberbullying detection. Through this analysis, this paper mainly focuses to the development of robust as well as scalable solutions for mitigating the adverse effects of cyberbullying in online communities.