An Efficacy Comparison of Supervised Machine Learning Classifiers for Cyberbullying Detection and Prediction
International Journal of Bullying Prevention, ISSN: 2523-3661
2024
Metric Options: CountsSelecting the 1-year or 3-year option will change the metrics count to percentiles, illustrating how an article or review compares to other articles or reviews within the selected time period in the same journal. Selecting the 1-year option compares the metrics against other articles/reviews that were also published in the same calendar year. Selecting the 3-year option compares the metrics against other articles/reviews that were also published in the same calendar year plus the two years prior.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Example: if you select the 1-year option for an article published in 2019 and a metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019. If you select the 3-year option for the same article published in 2019 and the metric category shows 90%, that means that the article or review is performing better than 90% of the other articles/reviews published in that journal in 2019, 2018 and 2017.
Citation Benchmarking is provided by Scopus and SciVal and is different from the metrics context provided by PlumX Metrics.
Article Description
In the face of increasing cyberbullying incidents on online social networking sites (SNS), there is a growing demand for robust detection and prediction mechanisms to foster a safer digital environment. This paper investigates the performance of several supervised machine learning (ML) classifiers in terms of sentiment analysis and text categorization related to cyberbullying. It introduces frameworks for text pre-processing and classification with multiple cyberbullying classes like religion, age, gender, and ethnicity. Utilizing a comprehensive dataset of cyberbullying incidents collected from X (formerly Twitter), this study evaluates multiple supervised learning classifiers to identify the best one with the highest accuracy. The best-performing classifier is then used to develop a robust model for cyberbullying detection and prediction. In addition, feature extraction and model interpretability are achieved to learn more about how these classifiers make decisions when it comes to cyberbullying. The main aim of this research is to contribute practical solutions by identifying the most suitable machine learning models for diverse social networking sites datasets. Through performance evaluation, it is observed that the Random Forest classifier achieves an accuracy of 94%, outperforming the other classifiers and it is selected for the model development. Further, the developed model is trained, tested, and validated on different SNS platform datasets. Finally, the developed model is able to accurately perform detection and prediction of cyberbullying text as per the specified classes. This study has the potential to improve the model by applying deep learning and natural language processing (NLP) techniques to effectively detect cyberbullying in cyberspace.
Bibliographic Details
Springer Science and Business Media LLC
Provide Feedback
Have ideas for a new metric? Would you like to see something else here?Let us know