Mining the impact factors of threads and participators on usenet using link analysis

Abstract

Usenet is a world-wide distributed discussion system, and it is one of the representative resources on Internet. The structure of newsgroup on Usenet forms gradually along with the evolution of the newsgroup and could provide helpful information for the users. In this paper, we present a method to evaluate the impact factors of participators and threads based on the structure of newsgroup. Some analysis and experimental results on real data sets are also provided. The impact factors could provide useful intrinsic information of the newsgroup and can be used in some applications to help access information more efficiently on the Usenet. The method can be also applied on other discussion systems, such as web forums, bulletin board systems, and so on. © Springer-Verlag Berlin Heidelberg 2007.