Paper Title
Advanced Cyberbullying Detection and Prevention System Using LSTM (DL) Model

Abstract
Cyberbullying is a major concern in online communities, frequently leading to severe emotional distress and social isolation.This research presents a cyberbullying detection and prevention system that employs Long Short-Term Memory (LSTM) networks to analyze user-generated text to calculate a bullying percentage for every sentence. The system continuously monitors user behavior, dynamically reducing a reputation score based on detected bullying content. When a user's reputation score falls below a predefined threshold, they are automatically blocked from further interaction on the platform. By integrating deep learning and a reputation-based penalty mechanism, this system aims to mitigate cyberbullying incidents while maintaining a fair and proactive moderation process. The solution provides a scalable and effective approach for promoting healthier online environments. Statistical analyses reveal that our proposedmodeloutperformsitscounterparts,achievinga0.98accuracyandrecallratewith0.97ofprecisionandF1scorein detecting cyberbullying tweets. Keywords - Deep Learning, Bullying Percentage, Reputation Score,CyberbullyingDetection,Natural Language Processing(NLP),Long Short-TermMemory (LSTM), CyberbullyingPrevention, Social media, Recurrent Neural Network (RNN).