Massive Social Network Analysis: Mining Twitter for Social Good

摘要: Social networks produce an enormous quantity of data. Facebook consists over 400 million active users sharing 5 billion pieces information each month. Analyzing this vast unstructured data presents challenges for software and hardware. We present GraphCT, a Graph Characterization Toolkit massive graphs representing social network On 128-processor Cray XMT, GraphCT estimates the betweenness centrality artificially generated (R-MAT) 537 vertex, 8.6 edge graph in 55 minutes real-world (Kwak, et al.) with 61.6 vertices 1.47 edges 105 minutes. use to analyze public from Twitter, microblogging network. Twitter's message connections appear primarily tree-structured as news dissemination system. Within data, however, are clusters conversations. Using we can rank actors within these conversations help analysts focus attention on much smaller subset.