Community Structure and Information Flow in Usenet: Improving Analysis with a Thread Ownership Model

摘要: Studying Usenet provides unique insight into online communities, since there is often a pre-defined space for community interaction. Here, we examine large set of posts in nearly 200 politically-oriented newsgroups over period 4 years, using and novel approach to the analysis. Our study multi-scale: not only do individually compare measurements different groups, but also relationships between groups. Since users post multiple shared participating authors or cross may be way assess how closely related, content-wise, two groups be. However, this causes some confusion relevance. To combat effect, develop an “ownership” measure article cross-posted based on posting activity author. We show that ownership can greatly improve assessment information diffusion within suggest it analysis other problems.