An Application to Detect Cyberbullying Using Machine Learning and Deep Learning Techniques.

Area of Science:

• Computational Linguistics
• Social Media Analysis
• Artificial Intelligence

Background:

• Social media use has surged, increasing exposure to cyberbullying.
• Cyberbullying, often text-based, negatively impacts mental well-being.
• Automated detection systems are crucial for managing online harassment.

Purpose of the Study:

• To develop and evaluate a deep learning framework for real-time cyberbullying detection.
• To address the challenge of identifying cyberbullying across multiple languages.

Main Methods:

• A deep learning framework was proposed for analyzing social media posts.
• The system was designed to process real-time data from platforms like Twitter.
• Evaluation focused on the effectiveness of deep neural networks for text-based cyberbullying detection.

Main Results:

• The proposed deep learning framework demonstrated effectiveness in identifying cyberbullying content.
• The system successfully processed and analyzed multilingual data, including English, Hindi, and Hinglish.
• Deep neural network approaches proved superior to conventional methods in this context.

Conclusions:

• The developed system offers a robust solution for automated cyberbullying detection.
• The framework's multilingual capabilities enhance its applicability across diverse user bases.
• This research contributes to creating safer online environments through intelligent content moderation.