A Model for Geographic Knowledge Extraction on Web Documents

There is an increasing interest on doing research in the field of information retrieval which aims to incorporate new dimensions, apart from text based retrieval, to the Web search engines. Geographical Information Retrieval (GIR) aims to index Web resources using a geographic context. The process of identifying the geographic context starts with the detection of different types of geographic references associated to the documents, as for example, the occurrence of place names. This paper presents a model for detecting geographic references in Web documents based on a set of heuristics. Moreover, new concepts and methods for disambiguation of many places with the same name are addressed. Finally, a prototype was built, called GeoSEn which aimed to validate the effectiveness of the proposed model.