Experimental Evaluation of Cross-Platform Recognition of Identical and Unknown Users over Social Networking Environment

The capacity to individually identify and categorize people across sites and apps is vital for trustworthiness, fraud prevention, and personalized experiences in online social networking. In this study, strategies for platform identification among similar and unknown social networking users are evaluated. We study strategies that employ user attributes, behavior history, and inter-network connections to match profiles on multiple platforms and uncover new, previously connected people. This cross-validation on the proposed method uses Social Linkage Identification Strategy (SLIS) and Friend Relationship Evaluator. According to quantitative experiment results, our approach improves search people across multiple social networks more than FRE. The extensive social connection web in many online social networks is used to enhance user identification and verification via the Friend Relationship Evaluator (FRE) system. Our process uses advanced machine learning and data fusion to handle a wide variety of natural ventilation phenomena from different sensors and platform formats. We evaluate attribute-based matching, graph approaches, and behavior analytics for accuracy, scalability, and computing cost. This study advances user identification systems across digital platforms and helps service providers and end-users establish more sophisticated online identity management strategies.