Cyberbullying Detection Using Machine Learning:A Comprehensive Review
Year: 2026
Type: article
Study design: Systematic Review
Abstract: The rapid growth of social media platforms and online communication technologies has increased the scale of digital interactions while simultaneously introducing serious challenges related to harmful online behavior such as cyberbullying. Cyberbullying involves the use of digital platforms to harass, threaten, or humiliate individuals, often causing significant psychological and emotional harm. With the massive volume of user-generated content shared across social networking sites, detecting such harmful behavior through manual moderation has become increasingly difficult. As a result, machine learning techniques have emerged as an effective approach for automatically identifying cyberbullying in online environments. This study applies a systematic literature review (SLR) approach to examine research published over the past decade (2015–2025) on cyberbullying detection using machine learning methods. The review analyzes existing studies to understand commonly used algorithms, datasets, feature extraction techniques, and evaluation strategies applied in cyberbullying detection systems. It also highlights the role of natural language processing and deep learning approaches in improving the identification of abusive online content. In addition, the study discusses key challenges associated with cyberbullying detection, including contextual language understanding, sarcasm interpretation, dataset imbalance, and multilingual communication. This comprehensive analysis aims to provide researchers and practitioners with a clearer understanding of current developments and potential future directions in automated cyberbullying detection for safer online environments.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7218274645