Detecting Cyberbullying in Social Commentary Using Supervised Machine Learning

This paper addresses the problem of cyberbullying on various online discussion forums in the form of social commentary. Here, supervised machine learning algorithms are employed to detect whether a particular comment is an insult, threat or a hate message. First of all, a machine learning model is developed with Logistic Regression, Random forest and naive bayes algorithms for classification and then, both Voting and AdaBoost classifiers are applied on the developed model to observe which works best in this case. In Japan, the members of PTA (Parent Teacher Association) perform net-petrol with a manual website monitoring in order to catch and stop cyberbullying activities; however, doing all this manually is very time consuming and hectic process. The main contribution of this paper includes a mechanism to detect cyberbullying and by using supervised machine learning with logistic regression algorithm, model has achieved an accuracy of 82.7%. With voting classifier, an accuracy of 84.4% was observed. The evaluation results show that voting classifier outperforms all other algorithms in detecting cyberbullying.