ABSTRACT:With the widespread adoption of social media platforms such as Facebook, Instagram, and Twitter, online communication has become an integral part of everyday life. However, this digital transformation has also led to the emergence of cyberbullying, a serious social issue affecting individuals across all age groups, particularly adolescents. Cyberbullying involves the use of electronic communication to harass, threaten, or humiliate individuals, often leading to severe psychological consequences such as anxiety, depression, and, in extreme cases, suicidal tendencies. Detecting cyberbullying manually is a complex and time-consuming task due to the massive volume of usergenerated content and the subtle, context-dependent nature of abusive language. This research proposes a machine learning and natural language processing (NLP)-based approach to automatically detect cyberbullying in social media text. The study utilizes text preprocessing techniques and implements classification algorithms such as Logistic Regression, Support Vector Machine (SVM), and Random Forest. The performance of these models is evaluated using standard metrics including accuracy, precision, recall, and F1-score. The findings indicate that machine learning-based models can effectively identify bullying content, making them a promising solution for enhancing online safety and moderating harmful interactions on digital platforms.

KEYWORDS:Cyberbullying Detection, Machine Learning, Natural Language Processing, Social Media Analysis, Text Classification.

CYBERBULLYING DETECTION ON SOCIAL MEDIA USING MACHINE LEARNING AND NATURAL LANGUAGE PROCESSING

PRASAD RAJENDRA KHANVILKAR
STUDENT–CDOE, MUMBAI UNIVERSITY