Detection of Cyberbullying in Social Media Texts Using Explainable Artificial Intelligence

The widespread use of social media has opened the door to new forms of harassment and abuse, such as cyberbullying, that have a serious impact on individuals’ psychological health. Therefore, research communities have recently developed detection approaches using Natural Language Processing (NLP) combined with machine learning algorithms to identify instances of cyberbullying in social media texts. However, they are unable to determine the type of cyberbullying and the reasons why victims may be targeted. This paper develops a novel detection approach that can identify the type of cyberbullying based on characteristics such as gender, religion, age, and ethnicity, even if the original records in the training dataset do not include such information or features. This paper has accomplished this objective by utilizing Explainable Artificial Intelligence (XAI) technology alongside machine learning models to justify and explain the classification of text as cyberbullying. Technically speaking, XAI technology enables machine learning models to capture and highlight the most influential words that affect the decision to classify a text as cyberbullying. Those influential words are utilized to re-label and update the training data. The machine learning models are then re-trained using the updated data. To evaluate the performance of the proposed approach, a simulation experiment has been conducted on a large dataset containing texts from Twitter. Simulation results show that XAI technology provides convincing explanations for classifying a text as cyberbullying. It also enables machine learning models to identify various types of cyberbullying and enhances their performance in terms of classification accuracy.