A Semantic Similarity Measure for Conceptual Web Services Classification

Abstract

Classifying Web services into functionally similar groups is an efficient way to enhance services discovery, composition, and substitution processes. In order to ensure such efficiency, the classification process should rely on adequate semantic similarity measures. This paper presents a practical approach to measure the similarity of Web services. Both semantic and syntactic descriptions are integrated through specific techniques for computing similarity measures between services. Formal Concept Analysis (FCA) is used then to classify Web services into concept lattices in order to facilitate relevant services identification for composition and/or substitution purposes. The proposed similarity measure is evaluated and compared to some of the best-known existing ones. Results show a significant improvement of precision and recall of relevant services discovery for further composition and substitution tasks.