Cyberbullying Detection and Prevention for Women's Safety on Social Media
T. Hariharan, P Kanishkar, Mohammed Roshan S, K. Poongodi · 2025
The rapid growth of social media has revolutionized global communication, enabling individuals to connect, share ideas, and express themselves. However, this digital transformation has also given rise to harmful behaviors such as cyberbullying, which disproportionately affects women and other vulnerable groups. Cyberbullying involves the use of digital platforms to harass, intimidate, or harm individuals through offensive language, hate speech, and aggressive interactions. This paper proposes a machine learning-based framework for detecting cyberbullying, leveraging the Boost algorithm alongside advanced text preprocessing, feature extraction, and dimensionality reduction techniques. The proposed system achieves an F1-score of 0.96, outperforming traditional machine learning models such as Logistic Regression, Random Forest, and K-Nearest Neighbors. By automating the detection of harmful content, this framework aims to create safer online environments and support targeted interventions to protect women from cyberbullying.