Word embedding for detecting cyberbullying based on recurrent neural networks

Abstract

The phenomenon of cyberbullying has spread and has become one of the biggest problems facing users of social media sites and generated significant adverse effects on society and the victim in particular. Finding appropriate solutions to detect and reduce cyberbullying has become necessary to mitigate its negative impacts on society and the victim. Twitter comments on two datasets are used to detect cyberbullying, the first dataset was the Arabic cyberbullying dataset, and the second was the English cyberbullying dataset. Three different pre-trained global vectors (GloVe) corpora with different dimensions were used on the original and preprocessed datasets to represent the words. Recurrent neural networks (RNN), long short-term memory (LSTM), Bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and Bidirectional GRU (BiGRU) classifiers utilized, evaluated and compared. The GRU outperform other classifiers on both datasets; its accuracy on the Arabic cyberbullying dataset using the Arabic GloVe corpus of dimension equal to 256D is 87.83%, while the accuracy on the English datasets using 100 D pre-trained GloVe corpus is 93.38%.