We propose a novel Web services clustering framework by considering the word distribution of WSDL documents and tags. Typically, tags are annotated to Web services by users for organization. In this paper, four strategies are proposed to integrate the tagging data and WSDL documents in the process of service clustering. Tagging data is inherently uncontrolled, ambiguous, and overly personalized. Two tag recommendation approaches are proposed to improve the tagging data quality and service clustering performance. Comprehensive experiments demonstrate the effectiveness of the proposed framework using a real-world dataset.
