A Systematic Review: Detection of Anomalies in Social Networks

As the Internet is growing drastically, interest in online social networks has also dramatically increased over the past ten years. They are among the most widely used websites on the Internet, with applications in practically every aspect of life, including telemarketing, entertainment, healthcare, and business. However, as they are being used broadly, they have become the main targets for malevolent individuals who try to engage in a wide range of fraudulent or unlawful activities and harm other users. Therefore, it is vital to detect unusual activity, especially in social networks, as this enables the identification of crucial data pertaining to the behavior of unusual individuals (Anomaly detection). It is challenging to identify unusual and unpredicted user behavior by diving into the network’s hidden patterns, as these users’ engagement patterns differ greatly from those of other users. Although numerous techniques have been created for identifying anomalies in various problematic environments, this discipline is quite new and expanding quickly. As a result, this growing field of anomaly identification in social networks requires systematic analysis. By following the systematic literature review practice, the most relevant research papers from the data resources are selected by using search string keywords, de fi ne d inclusion/exclusion criteria, and the proper analysis of the selected research papers. The data collected is used to answer research questions. An exhaustive analysis of different techniques and approaches is performed by assessing them on the research methodology. This entire activity took around three to four months for a thorough analysis of relevant research papers. Upcoming researchers may work on the research gaps by checking on the proposals mentioned in this review paper.