An ontology-based cluster analysis framework

ABSTRACT

The main objectives of this paper is to propose a conceptual and software environment in which different aspects of cluster analysis of ontology-based data could be studied. The ontology-based dataset has two core components: description of categories and description of objects and relationships between them. Similarity between objects is defined as an amalgamation function of taxonomic, relationship and attribute similarity. The different measures to calculate similarity can be used. Further research is needed in order to evaluate these measures. The creation of a software tool which allows for classification of ontology-based data and comprehensive analysis of results is essential for the research in the area of ontology-based data mining. Such a tool should be universal, extensible and open. The universality manifests itself in the possibility of processing any data sets described by OWL tailored to meet individual requirements. The system extensibility means that it can be enriched with new elements without the necessity of making changes in its main elements. The openness enables the communications with other data analysis systems. In the paper theoretical aspects of cluster analysis of ontology-based data sets are presented. Next, a framework of cluster analysis system is outlined. Finally, some technical details of the system implementation are discussed.

REFERENCES

• 1: Budanitsky, A., and Hirst, G. 2001. Semantic Distance in WordNet: An Experimental, Application-oriented Evaluation of Five Measures. Workshop on WordNet and Other Lexical Resources. In the North American Chapter of the Association for Computational Linguistics (NAACL-2000), Pittsburgh, PA.
• 2: Jérôme Euzenat , Pavel Shvaiko, Ontology Matching, Springer-Verlag New York, Inc., Secaucus, NJ, 2007
• 3: Gruber, T. 1995. Toward Principles for the Design of Ontologies Used for Knowledge Sharing. In Formal Ontology in Conceptual Analysis and Knowledge Representation, N. Guarino and R. Poli (eds), Kluwer Academic Publishers.
• 4: Jiawei Han , Micheline Kamber, Data mining: concepts and techniques, Morgan Kaufmann Publishers Inc., San Francisco, CA, 2000
• 5: Jaro, M. A. 1995. Probabilistic linkage of large public health data file. Statistics in Medicine 14, 491--498.
• 6: Alexander Maedche , Steffen Staab, Measuring Similarity between Ontologies, Proceedings of the 13th International Conference on Knowledge Engineering and Knowledge Management. Ontologies and the Semantic Web, p.251-263, October 01-04, 2002
• 7: Alexander Maedche , Valentin Zacharias, Clustering Ontology-Based Metadata in the Semantic Web, Proceedings of the 6th European Conference on Principles of Data Mining and Knowledge Discovery, p.348-360, August 19-23, 2002
• 8: Christopher D. Manning , Hinrich Schütze, Foundations of statistical natural language processing, MIT Press, Cambridge, MA, 1999
• 9: Schickel-Zuber, V., Faltings, B. 2007. OSS: A Semantic Similarity Function based on Hierarchical Ontologies. In IJCAI, 551--556.
• 10: Winkler, W. E. 1999. The state of record linkage and current research problems. Statistics of Income Division. Internal Revenue Service Publication R99/04.
• 11: Zhang, X., Jing, L., Hu X., Ng M. and Zhou, X. 2007. A Comparative Study of Ontology Based Term Similarity Measures on PubMed Document Clustering. http://www.pages.drexel.edu/~xz38/pdf/209_Zhang_DASFAA07.pdf

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications

General Terms:
Algorithms, Measurement

Keywords:
cluster analysis, data analysis, data mining, ontology, similarity measures