A. Keyword distances The key requirement for stage one is a method of evaluating the similarity or distance between two areas of research, represented by appropriate keyword pairs. Existing studies have used methods such as citation analysis [Saka and Igami, 2007], [Small, 2006] and author/affiliation-based collaboration patterns [Zhu and Porter, 2002], [Anuradha et al., 2007] to extract the relationships between researchers and research topics. However, these approaches only utilize information from a limited number of publications at a time, and often require that the text of relevant publications be stored locally (see [Zhu and Porter, 2002], for example). As such, extending their use to massive collections of hundreds of thousands or millions of documents would be computationally unfeasible. Instead, we choose to explore an alternative approach which is to define the relationship between research areas in terms of the

For more information, please visit our website at

I. Abstract—Ontological concept evaluation is a difficult task. Till now, it is done either by domain expert or a knowledge base (thesaurus, ontology, etc.). In this research, we propose a new evaluation method based on a large web document collection, several context definitions deduced from it and three criteria. It provides a support for either a domain expert or a novice user. Moreover, it facilitates the semantic interpretation of the word clusters and consequently the ontological concept generation. Our contribution is to propose an evaluation framework that does not depend on a gold standard, could be applied to any domain even if expert intervention is not available and provides qualitative and quantitative criteria. Our experiments show how our method assists and facilitates the evaluation task for the domain expert. Index Terms—Ontology, concept, evaluation, semantic web, context I.

For more information, please visit our website at

41 42 43 44 45 46 47 48 49 50 51 52

Abstract not found

Abstract not found