a large-scale news paper analysis system that is able to create "entity datamaps", a spatial visualization of the interest in a given named entity. the aim of this system is to identify entities which display regional biases, by estimating the frequency of reference of an entity in any given city.
entities likely to be geographically-biased include United States cities & local sports teams. entities likely to have little bias include foreign cities, country names, & national political figures. The text is acquired from about 800 US online newspaper sources.
[link: sunysb.edu (pdf)]