CYBERBULLYING DETECTION IN SOCIAL MEDIA USING SUPERVISED LEARNING

The increasing prevalence of social media platforms has led to a rise in cyberbullying incidents, which can have severe psychological and emotional consequences for victims. Detecting cyberbullying in large-scale social media content is a challenging task due to the diverse nature of online interactions, including slang, sarcasm, and varying contexts. This paper explores the use of supervised learning techniques to detect cyberbullying in social media posts. By leveraging labeled datasets that classify text as either cyberbullying or non-cyberbullying, I employed a machine learning algorithm called Support Vector Machines (SVM) model to identify and classify harmful content. The performance of these models is evaluated using metrics such as accuracy, precision, recall, Support and F1-score. The results demonstrate that supervised learning models can effectively identify cyberbullying behavior, with Support Vector machine approaches offering superior performance in terms of classification accuracy. This study highlights the potential of machine learning for mitigating cyberbullying by automating the detection process, providing a foundation for real-time monitoring systems on social media platforms.