Deep KNN Based Text Classification for Cyberbullying Tweet Detection

Nowadays, cyberbullying is a serious issue that many businesses must deal with. Existing technology makes use of machine learning to automatically detect cyberbullying. Deep learning-based algorithms have been shown to achieve higher accuracy in text classification than existing methods. In this paper, we develop a cyberbullying tweets detection using machine learning algorithm. The proposed method reads the tweets and then classifies the texts relating to cyberbullying and blocks the users. The study uses a k-NN classifier integrated with Deep Learning and show how effective the model is over large text datasets than other methods. The results of simulation shows that the proposed method has higher rate of classification accuracy than the other existing methods.