Cyberbullying Detection by Using Artificial Neural Network Models

Cyberbullying is a rising problem in worldwide and also Turkey is suffering from this problem dramatically. According to researches, the rate of children that are victims of cyberbullying actions in Turkey was tripled in the last seven years and increased to 20%. On the other hand, considering literature there are only a few studies about the detection of cyberbullying in Turkish contents. Thus, we designed eight different artificial neural network models to detect cyberbullying in Turkish social media contents automatically in our study. These models along with various text mining techniques were experimented in the dataset that includes 3000 Turkish tweets. According to the evaluation results, the most successful model for predicting cyberbullying content is YSA2 with 91% F-measure score. Additionally, YSA2 gives better performance than the experimented machine learning classifiers in our previous study.