DETECTION OF CYBERBULLYING ON SOCIAL MEDIA USING MACHINE LEARNING

This review paper explores the application of advanced machine learning techniques, particularly Long ShortTerm Memory (LSTM) models, for detecting cyberbullying on social media platforms.With the increasing prevalence of cyberbullying, it has become essential to develop effective methods for identifying harmful content in real-time.LSTM models, known for their ability to process sequential data and capture long-term dependencies, are well-suited for analyzing text data from social media.The paper discusses various approaches for implementing LSTM based systems, evaluates their performance, and highlights the challenges faced in cyberbullying detection, including data imbalance, privacy concerns, and real-time processing requirements.Additionally, it reviews the impact of data preprocessing, feature extraction, and model optimization techniques in enhancing the accuracy of detection systems, ultimately providing a comprehensive understanding of the state-of-the-art methods in the field.