An Exploration Of Understanding Heterogeneity Through Data Mining

Development of internet and Web have resulted in many distributed information resources which in general are structurally and semantically heterogeneous even in the same domain. However, heterogeneity itself has not been studied in a formal way so that the representation of different kinds of heterogeneities can be generically processed by other programs automatically. Most descriptions and categorization schemes of heterogeneities were given in languages specific to different research groups. We believe that efforts invested in a thorough research of heterogeneity can ultimately benefit both data integration and data mining communities. In this paper we give a brief survey of various ways to categorize heterogeneity in the literature, and then performed a case study on detecting a specific class of heterogeneity in the setting of Semantic Web ontologies‐the one that can be discovered by only data-driven approaches. Finally we propose an automatic ontology matching system that can detect this heterogeneity by using redescription mining techniques. We also believe that automatic ontology matching process is a helpful step in tasks of mining multiple information sources in the heterogeneous scenario.