Local community detection algorithm based on hierarchical clustering

Aiming at the complexity of community detection algorithms and the problem of insufficient consideration of adjacency relations between nodes, we propose a hierarchical local community recognition algorithm. In order to improve the efficiency, the algorithm firstly preprocesses the datasets by removing 1-shell nodes on the premise of disaffecting the network structure. Secondly, extract K highest degree nodes of large scale networks once and take the core nodes and nodes connected directly with them as research objects to carry out the hierarchical distance measure. Lastly, set different threshold and take different extension according to the different clustering coefficient to decide whether the pair of nodes attributes to the same community thereby realize the community detection. Experiments on real world networks and artificial networks show the feasibility and efficiency of the algorithm. Copyright © 2015 Binary Information Press.