Skip to Main Content
With more and more Web services available on the Internet, many approaches have been proposed to help users discover and select desired services. However, existing approaches heavily rely on the information in UDDI repositories or WSDL files, which is quite limited in fact. The limitation of information weakens the effectiveness of existing approaches. In this paper, we present a novel Web services search engine named CoWS, which enriches Web services information using the information captured from the Internet to provide quality-aware Web services search. The information captured can be classified into two groups: functional descriptions and subjective feedbacks. We use the functional descriptions to enrich descriptions of Web services and the subjective feedbacks to calculate Web services' reputation. CoWS first ranks the services according to their functional similarities to a user's query, which are calculated using both descriptions in WSDL files and the enriched descriptions, and then refines and re-ranks the services with both objective quality constraints (QoS) and subjective quality constraints (reputation). The experiments on a large-scale dataset (including 31,129 Web services) show that CoWS can improve the effectiveness of both Web services discovery and selection comparing with existing approaches.
Date of Conference: 4-9 July 2011