Real-Time Cyberbullying Detection on Social Media Using Artificial Intelligence

Cyberbullying on social media has become a serious issue, and most existing systems act only after harmful content is delivered. In this work, a real-time detection and prevention system is developed to analyze messages before they reach the user. The model combines BERT for understanding context and BiLSTM for capturing sequence patterns. The system is implemented using a web-based architecture with real-time processing support. Experimental results show high accuracy and fast response, making it suitable for practical use. However, the model is currently tested only on English datasets and requires further validation for real-world deployment.