Enhancing cyberbullying detection: a comparative study of ensemble CNN–SVM and BERT models

Technological improvements have increased the number of people who use online social networking sites, resulting in an increase in cyberbullying. Bullies can attack victims through a large network of online social networking platforms. Cyberbullying is an umbrella term encompassing a wide range of online abuse, including but not limited to harassment, doxing, and reputation attacks. These attacks frequently leave the victim(s) with persistent mental scars, leading to desperate measures such as depression, self-harm, and suicidal thoughts. Given the effects of cyberbullying, there is an urgent need to prosecute and prevent such crimes. This paper gives a comprehensive review as well the empirical analysis of the machine learning, ensemble based and transformer-based models for the cyberbullying detection. This paper proposes two architectures to efficiently detect cyberbullying pattern. The proposed ensemble model makes use of CNN to extract the relevant features and the classification is performed by the SVM. Another proposed architecture utilizes the pre-trained model BERT to detect cyberbullying behavior on online platforms. Both the proposed models were tested on two separate datasets and achieved maximum accuracy of 96.88 and 97.34% for ensemble and BERT models, respectively. This paper provides a thorough examination of the various methodologies used for cyberbullying detection and conducts an empirical and comparative analysis of the presented models with traditional and current algorithms.