The role of geographic knowledge in sub-city level geolocation

Geolocation of microblog messages has been largely investigated in the literature. Many solutions have been proposed that achieve good results at the city level. Existing approaches are mainly data-driven (i.e., they rely on a training phase). However, the development of algorithms for geolocation at sub-city level is still an open problem. In this paper, we investigate the role that external geographic knowledge can play in geolocation approaches. We show how different geographical data sources can be combined with a semantic layer within a knowledge base to achieve reasonably accurate sub-city level geolocation.