Building a Geographical Ontology for Intelligent Spatial Search on the Web

Abstract

All aspects of human activity are rooted in geographic space in some respect. As a consequence, many web resources include references to geographic context. In order to assist in recognising spatial terms employed in a query, it is proposed to use a geographical ontology. A geo-ontology play a key role in the development of spatially-aware search engine, with regards to providing support for query disambiguation, query expansion, relevance ranking and web resource annotation. This paper describes the geo-ontology designed for the SPIRIT system, before focussing on the problem of integrating multiple datasets for constructing such an ontology. Similarity checking of datasets is an essential step in the process of integration. The validity and effect of the different measures are studied by building a prototype geo-ontology utilising different datasets. The experimental results obtained confirmed the effect of quality of the datasets and the importance of the flexibility of the technique proposed for adjusting the similarity measures to handle such an effect.