An automata algorithm for generating trusted graphs in online social networks

Online social networks (OSNs) are becoming a popular tool for people to socialize and keep in touch with their friends. OSNs need trust evaluation models and algorithms to improve users' quality of service and quality of experience. Graph-based approaches make up a major portion of existing methods, in which the trust value can be calculated through a trusted graph. However, this approach usually lacks the ability to find all trusted paths, and needs to put some restrictions to admit the process of finding trusted paths, causing trusted relations to be unreachable and leading to reduced coverage and accuracy. In this paper, graph-based and artificial intelligence approaches are combined to formulate a hybrid model for improving the coverage and accuracy of OSNs. In this approach, a distributed learning automata, which can be used to find all trusted relations without limitation, is employed instead of well-known graphic-based searching algorithms such as breadth-first search. Simulation results, conducted on real dataset of Epinions.com, illustrate an improvement of accuracy and coverage in comparison with state-of-the-art algorithms. The accuracy of the proposed algorithm is 0.9398, a 6% increase in accuracy over existing comparable algorithms. Furthermore, by the successful removal of imposed restrictions in the existing searching process for finding trusted paths, this algorithm also leads to a 10% improvement in coverage, reaching approximately 95% of all existing trusted paths. (C) 2022 Elsevier B.V. All rights reserved.