AI-Powered Frameworks for the Detection and Prevention of Cyberbullying Across Social Media Ecosystems
Year: 2025
Type: article
Abstract: This study presents an advanced AI-powered framework to detect and prevent cyberbullying across diverse social media platforms using a multiclass classification approach. Addressing the growing complexity and linguistic diversity of online abuse, the research integrates various machine learning (RF, LR, SVM) and deep learning (Bi-LSTM, BERT) models trained on a balanced dataset covering bullying categories based on religion, age, ethnicity, gender, and neutral content. Data preprocessing, tokenization, feature extraction via TF-IDF and CountVectorizer, and class balancing using SMOTE were applied to enhance model accuracy. The proposed system further supports real-time detection through social media APIs, offering dynamic monitoring and intervention capabilities. Among the tested models, Random Forest and BERT achieved the highest classification performance with 94% accuracy. Despite its robust architecture, limitations include dependence on English-language datasets, exclusion of multimodal data (e.g., memes, audio), and API restrictions that challenge scalability. Future development will focus on incorporating vision-language models and optimizing the system for real-time, multilingual, and multimodal environments. This study contributes to digital safety efforts by proposing a scalable and adaptive detection system suitable for safeguarding users from evolving forms of online harassment.
Source: Techcomp Innovations
Authors: Md. Anas Mondol, Md. Ashaf Uddaula, Md. Safaet Hossain, Mst. Ayesha Siddika
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: hybrid
OpenAlex ID: W4411523325