Cyberbullying Detection in Group Chat Applications- A Review
Rakhi Bhardwaj, Ayush Billade, Srinivas Chenna, Atharva Deshpande, Vaishnavi Arthamwar · 2024
Cyberbullying in group chat applications has become an increasingly pressing issue in today's digital society, affecting users across various platforms. This review aims to explore and analyze the current techniques, methodologies, and challenges in detecting cyberbullying in group chat environments. By examining existing literature and approaches, we focus on how NLP, ML, and DL techniques are applied to identify harmful behaviors in real-time conversations. The review also highlights the complexities of analyzing unstructured text data, the role of sentiment analysis, and the need for context-aware models to detect subtle forms of harassment. Additionally, we investigate privacy concerns, ethical considerations, and the limitations of existing models in multilingual and culturally diverse groups. The paper emphasizes the importance of developing more robust, scalable, and adaptive detection systems to create safer online environments. This review concludes with future research directions, suggesting the integration of advanced AI techniques and collaborative efforts between researchers, developers, and policymakers to mitigate the growing cyberbullying problem in group chat applications.