摘要：Community discovery is, as the name implies, for founding useful community structure in the social network. So far, there are many mining the social network community algorithm and some of these algorithms have even got application in reality. However, it is important to note that most of the existed community discovery algorithms are only applicable to small and medium networks. This study proposes an improved k-means algorithm. First of all, the study uses two algorithms to obtain the initial clustering with high accuracy and adaptability. It can avoid the many processes after choosing the random initial value. Then this study uses the compression technology and B tree format to store community information which can effectively reduce the time complexity of matching nodes and space complexity of temporary data storage. Finally, this study proposes the timing and method of the trimming community so that it can get accurate community classification results in a small probability event.
