Fuzzy semantic similarity in linked data using the OWA operator

Semantic similarity measure becomes profoundly important and useful in many applications of linked data. In this paper, we provide a novel solution for determining similarity between concepts in linked data while allowing the importance of properties to influence the similarity measure. Our proposed approach is implemented based on feature-based similarity model, which considers the shared objects between the concepts. First, we develop a fuzzy membership function to capture the importance of different properties, and then use ordered weighting averaging (OWA) operator for aggregation of multiple similarity measures corresponding to different importance levels of properties. Experimental evaluations confirm the suitability of the proposed method.