Automatic detection of cyberbullying using multi-feature based artificial intelligence with deep decision tree classification

Recent studies have shown that cyberbullying is a rising youth epidemic. In this paper, we develop novel automated classification model identifies the texts without fitting them into large dimensional space. On other hand, classifier .cannot provide limited convergent solution due to its overfitting problem. Considering such limitations, developed text engine initially pre-processes tweets, eliminates noise and background information, extracts selected features classifies data overfitting. The study develops Deep Decision Tree utilizes hidden layers of Neural Network (DNN) as tree node process input elements. validation confirms accuracy using with improved .