DETECTION OF CYBERBULLYING USINGMACHINE LEARNING

The advent of the digital age has enabled people to a new form of bullying which often results in social stigma. This new
form of bullying is Cyber bullying which is a crime in which a perpetrator targets a person with online harassment and
hate. Social networks provide a rich environment for bullies to find and harass vulnerable victims. Messages or comments
concerning sensitive topics that are personal to an individual are more likely to be internalised by a victim, often ending in
tragic outcomes. This phenomenon is creating a demand for automated, data-driventechniques for analysing and detecting
such behaviour on the internet. In this project, a machine learning-based approach is proposed to detect cyber bullying
activities from social network data. Naïve Bayes classifier is used to classify the type of message i.e., cyber bullying and
non-cyber bullying message. Messages and take necessary actions. Our evaluation of performance results reveals that the
accuracy of the proposed approach increases with more classification data.