Investigating Similarity of Ontology Instances and Its Causes

In this paper we present a novel method of comparing instances of ontological concepts in regard to personalized presentation and/or navigation in large information spaces. It is based on the assumption that comparing attributes of documents which were found interesting for a user can be a source for discovering information about user’s interests. We consider applications for the Semantic Web where documents or their parts are represented by ontological concepts. We employ ontology structure and different similarity metrics for data type and object type attributes. From personalization point of view we impute reasons that might have caused user’s interest in the content. Moreover, we propose a way to enumerate similarity for the particular user while taking into account individual user’s interests and preferences.