DETECTION OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING AND DEEP LEARNING

Abstract

The rapid expansion of social media platforms has revolutionized communication, allowing individuals to connect and share opinions globally. However, this growth has also led to an alarming rise in cyberbullying, where individuals are subjected to harassment, hate speech, and online abuse. Traditional methods of detecting cyberbullying are often inadequate due to the vast amount of user-generated content and the evolving nature of online threats. To address this challenge, machine learning techniques have been explored to develop automated systems for detecting and mitigating cyberbullying in real time. This study focuses on utilizing machine learning algorithms to analyze social media posts and identify potential instances of cyberbullying. Various natural language processing (NLP) techniques, including sentiment analysis and keyword extraction, are employed to detect harmful or offensive language. Additionally, supervised learning models such as Support Vector Machines (SVM), Random Forest, and deep learning approaches like Recurrent Neural Networks (RNN) and transformers are leveraged to classify textual content effectively. The integration of these techniques enhances the system’s ability to recognize patterns associated with cyberbullying. A crucial aspect of this research is the development of a comprehensive dataset that encompasses diverse examples of cyberbullying across multiple social media platforms.