Associate Professor, IIT Kharagpur
Le 16/06/2016 à 11h00, salle 018, bâtiment Pascal.
Title : Title : Recommendation in Location Based Social Network
Abstract : The widespread popularity of location based social networks (like Foursquare, Yelp) in recent years have enabled users to share their location and geo-tagged information. In this work, we deal with two different recommendation problems in the LBSN platform (a) location recommendation (b) business recommendation.
The geo-social correlations in LBSN have been exploited to build systems that can recommend new locations to users. We demonstrate the impact of two new modalities - tips and reviews, on location recommendation. We propose a graph based recommendation framework which reconciles the `tip’ and `review’ space of Yelp in a complementary fashion. Next we consider a business owner’s perspective of recommending regions to setup new (popular) businesses. We study the role of information diffusion in shaping the popularity of businesses. We explore on two key modalities as the medium of information spread (a) social connections (b) geographical proximity.