关键词: 符号网络, 聚类算法, 网络簇, 随机游走, 启发式策略

Abstract: The Finding and Extracting Community (FEC) algorithm has some disadvantages as the algorithm stability is not enough, and the quality of extracting community needs to be improved. To solve these problems, some improvements were made from the following aspects: Add the function of selecting target vertex before random walk; cancel the parameter of random walk steps of the original algorithm by using a method of detecting steps automatically; supplement the quality evaluation of the link between the communities on the base of the original community extraction; achieve the controllability of particle size of community by introducing the threshold parameter. The results show that the improved algorithm has some improvements at the aspects of stability, anti-jam performance and clustering analysis.

Key words: signed network, clustering algorithm, network community, random walk, heuristic strategy