Identifying, Attributing and Describing Spatial Bursts

User generated content that appears on weblogs, wikis and socialnetworks has been increasing at an unprecedented rate. The wealthof information produced by individuals from different geographicallocations presents a challenging task of intelligent processing.In this paper, we introduce a methodology to identify notablegeographically focused events out of this collection of user gener-ated information. At the heart of our proposal lie efficient algo-rithms that identify geographically focused information bursts, at-tribute them to demographic factors and identify sets of descriptivekeywords. We present the results of a prototype evaluation of ouralgorithms on BlogScope, a large-scale social media warehousingplatform. We demonstrate the scalability and practical utility of ourproposal running on top of a multi-terabyte text collection.