Measuring concept similarity in ontologies using weighted concept paths

Semantic similarity and relatedness between concepts have been extensively studied in different areas ranging from psychology to computational linguistics. In this paper we address the problem of determining the similarity between concepts defined in a knowledge source such as an ontology. The focus is measuring similarity between concepts from the same ontology. We propose a concept similarity algorithm based on geometric models for representing concepts and relationships, which can be applied to different types of ontologies. The key idea is the concept weighting scheme which allows for quantifying the degree of abstractness of concepts. The evaluation settings involving two ontologies validate and highlight the advantages and disadvantages of the proposed approach. Using the proposed measure, which closely resembles the human judgment of similarity, we can reliably recreate predefined concept clusters, and generate more informative concept paths.