An Enhanced Community Detection Metric for Weighted and Directed Graph-Based Network

Abstract

Community detection algorithm tries to find the densely connected units in a large network. For this objective different matrices have come into light. Most of them assume all the vertices in a community belong equally to the community. But these matrices identify the communities as whole, these doesn’t give any information at which content the nodes are connected in a community. Moreover these also face resolution limit for larger networks. For resolving this issue, another matrices named permanence has been applied. But this metric is not defined for weighted and directed graph. Our approach will be to implement the permanence on directed and weighted graph.