CLCLP: Overlapping Community Detection in Networks Using a Combination of Link Community and Label Propagation Algorithm

Abstract

Overlapping Community Detection is a tremendous method for accepting a crucial shape and complicated network software. As of overlapping communities descriptions of real-world networks must subsist quantified for community identification, this research suggested a method for discovering overlapping communities termed the Combination of Link Community with Label Propagation (CLCLP) algorithm. CLCLP converts a node separation issue into a link division issue because of its simplicity and competency of the label propagation technique, an improved label propagation algorithm that prioritizes connections over nodes to perceive communities has been developed. The proposed CLCLP then employs post-processing to develop discovered overlapping communities by removing over-overlapping and inaccurate fragile secures partitions. When tested on a large scale of synthetic and real-world networks, the proposed CLCLP approach attains good precision (i.e., accuracy) and NMI (Normalized Mutual Information) in recognizing overlapping communities in networks