Deep Learning Algorithms for Cyber-Bulling Detection in Social Media Platforms

Aim:

         To improve the accuracy and efficiency of cyberbullying detection in social media text by utilizing an advanced machine learning model (DistilBERT) that overcomes ambiguity and classification challenges.

Abstract:

      Cyberbullying detection on social media platforms is challenging due to the informal, ambiguous, and context-dependent nature of language. This project aims to enhance the accuracy of fine-grained cyberbullying classification using the DistilBERT model. By leveraging DistilBERT, the system improves classification, achieving angood accuracy using large tweet dataset. This model will outperform previous deep learning models like LSTM,BiLSTM and Bert.

Proposed System:

        This project proposes using the DistilBERT model to classify various types of cyberbullying, focusing on fine-grained detection. The system utilizes advanced machine learning techniques to handle ambiguous cases effectively, achieving high accuracy rates. The model has been evaluated on two tweet datasets, one with larger dataset with 100k tweet samples. It can achieves a high accuracy on the larger dataset, demonstrating significant improvements in performance compared to existing models.

Advantages:

• High performance in detecting cyberbullying-related hate speech.
• Effective handling of ambiguity using DistilBERT’s transformer-based architecture.
• High Accuracy: Achieved high accuracy with DistilBERT on the 100k tweet dataset.
• Handling Ambiguity: DistilBERT, with its transformer-based architecture, helps address ambiguity and improves the model’s ability to detect subtle variations in cyberbullying.