Answers are grounded in this paper and cite their sources.
Cyberbullying is a significant and increasing problem in online communities, and the detection system should also be effective in addressing it. The research presents an in-depth comparison of image classification systems such as Logistic Regression, Naive Bayes, XGBoost, Decision Tree, and Random Forest in the detection of cyberbullying. The evaluation of the five machine learning algorithms with respect to: Logistic Regression, Naive Bayes, XGBoost, Decision Tree, and Random Forest, will be within the framework of large-scale dataset collection about cyberbullying. This will be done based on the evaluation of the metadata file using accuracy, precision, recall, and F1 score, which represent the overall performance level. The results presented help determine the weaknesses and strengths of the individual algorithms and narrow the search for the right approach to cyberbullying detection. Moreover, best-performing algorithms were integrated into a Stream -lit- based front end for real-time prediction and display of the capabilities of the model. This study contributes significantly to the research on the development of new machine-learning solutions for cyberbullying detection and provides a solid evaluation of various classification strategies that are ultimately well-suited for effective detection systems in the future.
No takes yet. Share an insight, caveat, or question.
Kanitha et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: