A Multifaceted Framework for Identifying Prominent Cybercrime Nodes in Social Media Networks Using Random Walk and Fuzzy AHP

Social media cybercrime has increased tremendously, calling for sophisticated methods to identify and counter threats. This study suggests a Multilayer Model to Detect the Most Influential Node for Cybercrime in social media based on Random Walk and Fuzzy AHP. Social media information is modelled as a graph such that nodes represent users and edges represent interactions. To identify the most influential node of a cybercrime community, the model takes Degree Cardinality, Betweenness Cardinality, and Mean Distance as decisive parameters. A Random Walk Algorithm is run repeatedly four times to analyse and note these parameters for every node. Then, the Fuzzy Analytical Hierarchy Process (Fuzzy AHP) is used to rank the identified nodes according to their influence. The most influential node is ranked as the most important in the cybercrime network. The suggested model improves detection of cybercrime by offering a structured method for determining key offenders, which can help in proactive cybersecurity actions. Use of Fuzzy AHP makes the model intelligent by making decision on the basis of multiple parameters simultaneously.