Weighting links based on co-occurrence relationship for community detection enhancement

Abstract

Community detection in networks is a significant issue to understand the formation of network structures and quantify interactions. Proposed methods in recent years show that adding proper weights to links of a network provides appreciable contributions for community detection. Weighting links is an open problem because it is still not clear how to obtain proper weights from the structure of the network. In this paper, we propose a new method based on co-occurrence relationship among nodes in the network. It has been used for improving the performance of Newman's greedy algorithm. Experiments on synthetic and real-world datasets show that our method is efficient to increase modularity and accuracy. Results of comparative performance for several weighting methods also indicate that this method gives better outcomes than some well-known methods. © 2018 Elsevier B.V., All rights reserved.