Cascading Behavior in Large Blog Graphs

摘要: How do blogs cite and influence each other? such links evolve? Does the popularity of old blog posts drop exponentially with time? These are some questions that we address in this work. Our goal is to build a model generates realistic cascades, so it can help us link prediction outlier detection. Blogs (weblogs) have become an important medium information because their timely publication, ease use, wide availability. In fact, they often make headlines, by discussing discovering evidence about political events facts. Often one another, creating publicly available record how spreads through underlying social network. Aggregating from several creates directed graph which analyze discover patterns propagation blogspace, thereby understand Not only interesting on own merit, but our analysis also sheds light rumors, viruses, ideas propagate over computer networks. Here report surprising findings linking structure, after analyzed largest datasets, 45,000 ~ 2.2 million blog-postings. We present simple mimics spread blogosphere, produces cascades very similar those found real life.