PROJECT TITLE :

Linking Fine-Grained Locations in User Comments - 2018

ABSTRACT:

Several domain-specific websites host a profile page for each entity (e.g., locations on Foursquare, movies on IMDb, and product on Amazon) for users to post comments on. When commenting on an entity, users often mention other entities for reference or comparison. Compared with web pages and tweets, the matter of disambiguating the mentioned entities in user comments has not received abundant attention. This Project investigates linking fine-grained locations in Foursquare comments. We demonstrate that the focal location, i.e., the situation that a comment is posted on, provides wealthy contexts for the linking task. To exploit such data, we represent the Foursquare information in a very graph, which includes locations, comments, and their relations. A probabilistic model named FocalLink is proposed to estimate the chance that a user mentions a location when commenting on a focal location, by following completely different sorts of relations. Experimental results show that FocalLink is consistently superior under different collective linking settings.