Semantic Similarity based on Weighted Ontology - Geographical Information Systems: Trends and Technologies - page 324

regarding cardinal relations they are north , east , west , and south (Pourabbas
and Rafanelli 2002). Distance relations describe the spatial arrangement of
objects and the less precise forms of these types of relations are close to , and
far from . A further application of similarity methods is the comparison of two
or more categorical maps. This task occurs increasingly in remote sensing,
geographical information analysis, spatial modelling, and landscape
ecology. In many maps the defi nition of categories is vague, such as the ones
where the categories are defi ned on the basis of ordinal defi nition, such as
high , medium and low density incidence of a disease. Such cases also require
fuzzy-based similarity approaches to identify similar categories.
Third, how multiple geo-ontologies can be exploited in order to evaluate
the semantic similarity of concepts and consequently how the similarity
methods can be adapted to this context for achieving accurate results.
Fourth, extension of the approaches to the set of operations that can be
performed on geographic data. Fifth, the analysis of the applicability of the
methods to the massive corpus, like the Web. An interesting issue related to
the Web is the implementation of similarity methods for geographic data
based on Linked data (Heath and Bizer 2011) that signifi cantly increments
their usability in the Semantic Web. There are several proposals following
the Linked Data principles for defi ning vocabularies and describing data
(e.g., documents, people, etc.). Regarding the Linked Data initiatives, the
most popular is DBpedia, 8 which aims at extracting structured content from
Wikipedia and representing it in a RDF format. However, the exploitation
of Linked data to implement similarity methods is a challenging problem
to be investigated.

References

Baglioni, M., E. Giovannetti, M.V. Masserotti, C. Renso and L. Spinsanti. 2009. Ontology
supported Querying of Geographical Databases. Transactions in GIS. 12(s1): 34-44.
Balakrishnan, N. and V.B. Nevzorov. 2005. Discrete Uniform Distribution, in A Primer on
Statistical Distributions, John Wiley & Sons, Inc., Hoboken, NJ, USA.
Ballatore, A., D.C. Wilson and M. Bertolotto. 2012. Geographic Knowledge Extraction and
Semantic Similarity in Open Street Map, Knowledge and Information Systems (KAIS),
Springer, DOI: 10.1007/s10115-012-0571-0.
Beeri, C. 1990. A formal approach to object-oriented databases, Data & Knowledge Engineering,
North-Holland. 5: 353-382.
Buccella, A., A. Cechich and P. Fillottrani. 2009. Ontology driven geographic information
integration: A survey of current approaches. Computers & Geosciences. 35: 710-723.
Buccella, A., A. Cechich, D. Gendarmi, F. Lanubile, G. Semeraro and A. Colagrossi. 2011.
Building a global normalized ontology for integrating geographic data sources.
Computers & Geosciences. 37: 893-916.
Budanitsky, A. and G. Hirst. 2006. Evaluating wordnet-based measures of semantic distance,
Comput. Ling. 32: 13-47.

8

http://dbpedia.org