Ning Xia, 4th year EECS Ph.D. student, and his advisor Prof. Aleksandar Kuzmanovic won the Best Paper Award at the 2014 IEEE/WIC/ACM International Conference on Web Intelligence (WI 2014), taking place August 11-14 in Warsaw, Poland. Their winning paper was titled, “GeoEcho: Inferring User Interests from Geotag Reports in Network Traffic”, and was also co-authored by industry partners Stanislav Miskovic, Mario Baldi, and Antonio Nucci, all from Narus, Inc.
The paper features GeoEcho, a mobile traffic analyzer that extracts and analyzes a wealth of latitude-longitude geotag reports generated by smartphones, with the purpose of identifying the points of interest which people actually visit. The key challenge in such identification is that geotag reports are commonly sent arbitrarily, sparsely and without a sufficient accuracy to uniquely identify any point of interest. GeoEcho devises methods that effectively identify and prune irrelevant geo information and infer personal interests of individuals. The paper shows a significant GeoEcho usability in various contexts ranging from generic user profile and user group analysis, to advertising and security applications.
The WI conference focuses on scientific research and applications by jointly using Artificial Intelligence and Information Technology for the next generation of Web-empowered products, systems, services, and activities. The series of Web Intelligence (WI) conferences was started in Japan in 2001. Since then, WI has been held yearly in several countries including: Canada, China, France, USA, Australia and Italy. WI conference is recognized as the World’s leading forum related to Web Intelligence. This year, it is a part of the 2014 Web Intelligence Congress. It is organized in Warsaw, Poland, as a Special Event commemorating the 25th anniversary of the Web.