James Caverlee, PhD: Towards Web-Scale Semantic Crowd Discovery
In much the same way as web search engines provide instant access to the retrospective web of previously crawled and indexed content, there is a growing need to fundamentally advance research for enabling a new generation of applications for monitoring, analyzing, and distilling information from the prospective web of real-time content that reflects the current activity of the web’s participants. Highly-dynamic real-time social systems like Twitter, Facebook, and Google Buzz have already published exabytes of real-time human “sensor” data in the form of status updates. Coupled with growing location-based social media services like Gowalla, Foursquare, and Google Latitude, we can see unprecedented access to the activities, actions, and trails of millions of people, with the promise of deeper and more insightful understanding of the emergent collective knowledge (“wisdom of the crowds”) embedded in these activities and actions. Toward the goal of web-scale social media mining and inference, our lab (http://infolab.tamu.edu) is pursuing a set of related research activities, two of which I will discuss as part of this talk: (i) identifying and tracking the evolution of semantic crowds; and (ii) social media location estimation.
Prof. James Caverlee is currently a tenure-track faculty member in the department of Computer Science and Engineering at Texas A&M University. At Texas A&M, Dr. Caverlee directs the infolab, a research lab founded in 2007 to study problems at the intersection of web-scale information management, distributed data-intensive systems, and social computing. Dr. Caverlee received his Ph.D. from Georgia Tech in 2007, M.S. degrees in Computer Science (2001) and in Engineering-Economic Systems & Operations Research (2000) from Stanford University, and a B.A. in Economics from Duke University (1996, magna cum laude). Dr. Caverlee is a recipient of the 2010 Defense Advanced Research Projects Agency Young Faculty Award (DARPA YFA), two Google Research Awards (2008 and 2010), and has twice been awarded the Graduate Faculty Teaching Excellence Award (2009 and 2010).