Novel social network community discovery method combined local distance with node rank optimization function

Abstract

In view of that most of the current community discovery methods in social network do not consider node self-transfer and node bias, so that it is not possible to extract the graph features effectively, which leads to the ineffective problem by the community discovery, this paper proposes a novel social network community discovery algorithm (Local Distance Laplace, LDL). First, a Laplace matrix decomposition model is constructed based on the principle of matrix decomposition. Secondly, considering the high cost of global social network information acquisition and calculation, a community discovery model based on local distance is proposed. Finally, the optimal community structure is selected by using the NRO (Node Rank Optimization) function. A comprehensive comparative analysis is made on eleven real and synthetic networks. At the same time, validation analysis is conducted on eleven different social networks (Karate, Dolphins, Lemis, Public book, Football, Celegansnertal, Email, Public blogs, Netscience, Power, Hep_th). The experimental simulation results show that: in the real network, the proposed LDL algorithm improved the overall performance by nearly 7% compared with the seven state of art optimal methods (CoVeC, EDBC, JNMF, EADP, LPANNI, LSA, SCFS). The novel algorithm is reasonable and effective and it can also be extended to multi-scale community discovery.