Published Paper Details:

The exponential growth of Online Social Media (OSM) platforms has provided users with dynamic means of communication, content sharing, and interaction. However, this growth has also attracted malicious entities that exploit these platforms for spamming, spreading misinformation, and executing fraudulent activities. Traditional content-based and user-behavioral spam detection techniques often fall short in detecting sophisticated spam patterns. In response, network-based approaches have gained significant traction by leveraging the structural and relational properties of social networks. This comprehensive review explores the spectrum of network-centric methodologies used in spam detection, including graph-based models, community detection algorithms, propagation patterns, and trust networks. The paper categorizes and analyzes the state-of-the-art techniques, evaluates their strengths and limitations, and highlights emerging trends in network science applied to OSM spam detection. Furthermore, it discusses real-world datasets, performance metrics, and the integration of hybrid frameworks combining machine learning with network-based insights. This review serves as a valuable resource for researchers and practitioners aiming to develop robust and scalable spam detection systems in the dynamic landscape of online social platforms.