Community discovery method based on multidimensional social network

Abstract

The invention discloses a community discovery method based on a multi-dimensional social network. In the method, multi-level fusion is conducted on a friend relationship network, a comment relationship network, a recommendation forwarding relationship network and an interest similarity network in the social network to obtain the total correlation degree of users; then, with each user regarded as anode and the total correlation degree of the users taken as the transmission probability, the community is divided by the label propagation algorithm, so that social discovery is completed. As users'social behaviors are comprehensively considered and reasonable selection and fusion are conducted, the method has great accuracy and effectiveness.

Description

technical field [0001] The invention belongs to the technical field of data mining, and more specifically relates to a community discovery method based on a multidimensional social network. Background technique [0002] Usually, the network is abstracted into a graph. Users are represented by nodes in the graph, and relationships between users are represented by edges. The structure shown in this network is called a community. The connection density between nodes within a community is high, while the connection density between nodes in different communities is low. [0003] Community discovery is an effective method for analyzing social networks. As a research hotspot in the field of social network data mining, community discovery has been paid more and more attention by scholars. In the field of community discovery, many scholars have proposed or summarized some classic community discovery algorithms: [0004] 1. The document [Kernighn BW, LinS.A efficient heuristic proce...

AI Technical Summary

Problems solved by technology

[0004] 1. The document [Kernighn BW, LinS.A efficient heuristic procedure for partitioning graphs[J]. Bell System Techn-Ical Journal, 1970,49(2):292~307.] proposed the K-L algorithm, which is a heuristic optimization method. A gain function Q is introduced into the algorithm, and then the greedy algorithm principle is used to exchange node pairs to maximize the Q value. Finally, two communities with known sizes are divided. The disadvantage is that only two communities can be divided and two community members must be known. quantity;

[0005] 2. The literature [Girvan M, Newman M E J. Community structure in social and biological networks [J]. Proceedings of the National Academy of Science, 2002, 99 (12): 7821-7826.] proposed the GN algorithm, the GN algorithm The idea is that the betweenness of edges between communities is greater than the betweenness of edges within communities. By continuously removing the edges with the largest betweenness until the entire network degenerates into a community, the advantage of the algorithm is that it does not need to know the number of communities in advance, but Its calculation time complexity is high;

[0006] 3. The literature [Tang Lei, Wang Xufei, Liu Huan.Community detection inmultidimensional networks[R] / / Tec hnical Report TR10-006.Arizona:ArizonaState University,2010.] proposes an algorithm for solving multidimensional networks. Network integration, there are mainly four integration methods: network integration, utility integration, feature integration and partition integration, and then use spectral clustering method, random block model method or The hidden space model can divide the above-mentioned integrated network into communities, but the disadvantage is that they can only be used for medium-sized undirected networks, and are not suitable for community discovery in complex directed multi-dimensional social networks.

Images