Automatic Web service tagging using machine learning and WordNet synsets

Abstract

The importancy of Web services comes from the fact that they are an important means to realize SOA applications. Their increasing popularity caused the emergence of a fairly huge number of services. Therefore, finding a particular service among this large service space can be a hard task. User tags have proven to be a useful technique to smooth browsing experience in large document collections. Some service search engines proposes the facility of service tagging. It is usually done manually by the providers and the users of the services, which can be a fairly tedious and error prone task. In this paper we propose an approach for tagging Web services automatically. It adapts techniques from text mining and machine learning to extract tags from WSDL descriptions. Then it enriches these tags by extracting relevant synonyms using WordNet. We validated our approach on a corpus of 146 services extracted from Seekda. © 2011 Springer-Verlag Berlin Heidelberg.