Geographic scope modeling for web documents

Abstract

Geographic Information Retrieval (GIR) has become a very attractive area of research. GIR is a specialization of a traditional information retrieval system, which may index and search Web documents based on their spatial footprints. Research in this new field may be categorized into crawling spatial-related documents, modeling the geographic scope of a document, indexing these documents using textual and spatial features, and the building of spatially-enabled searching and ranking. This paper presents a method for modeling the geographic scope. The proposed model is based on both the statistics collected from the detected references; and the spatial distribution of the places involved in a given document. This model aims to simplify the indexing and searching processes. Furthermore, the number of spatial operations is reduced, as a consequence the overall performance is improved.