An Enhanced Approach For Web Services Clustering Using Supervised Machine Learning Techniques

1698 Words Dec 10th, 2016 7 Pages
An Enhanced Approach for Web Services Clustering using Supervised Machine Learning Techniques

Automatic document classification provides techniques that may improve and support web service clustering. As the number of services increases, the cost of classifying services through manual work increases. In this research, we presented an enhanced approach for service clustering that combines text mining and machine learning technology. The method only uses text description of each service so that it can classify different types of services, such as WSDL Web Service, RESTful Web Service. This approach provides better performance in terms of service discovery efficiency and effectiveness. In this approach, we identify four key features that can be extracted from WSDL documents and integrated to cluster web services into functionality-based groups. These features are WSDL content, types, referenced ontology, and web service name. our approach utilizes the supervised machine learning techniques such as Decision Trees, Deep Learning, and Naïve Bays classification methods. A comparison between the three techniques are made regarding the result accuracy and the computation cost.

Web service discovery is becoming difficult task because of increasing Web services available on the Internet. As seeking for efficient web service discovery is main challenge for researchers, research in cluster analysis of web services has recently gained much attention. This is due…
Open Document