Improving REST Service Discovery with Unsupervised Learning Techniques

JUAN MANUEL RODRIGUEZ; ALEJANDRO ZUNINO; CRISTIAN MATEOS; FÉLIX SEGURA; EMMANUEL RODRIGUEZ

Blumenau

Conferencia; 9th International Conference on Complex, Intelligent, and Software Intensive Systems (CISIS-2015) [Qualis B3]; 2015

Regional University of Blumenau (FURB)

Discovery and replacement are two of the main promises of Service Oriented Computing. There has been much research on this topic for traditional SOAP-based Web Services. Although the original propose for REST service lacks of this feature, some researchers have study how to perform discovery for REST services using both IR based techniques and semantic techniques. This work presents a novel IR-based discovery approach for REST services described via WADL files. Our approach takes advantage of unsupervised machine learning techniques for improving discovering results. This approach relies on clustering algorithms, such as K-means or X-means, to reduce the search space for a given query. The experimental results shows that using an appropriated a clustering technique, our approach reported nearly 4 times higher F-measure than a traditional IR-based search engine, namely Apache Lucene. Additionally, the experiments report other metrics, such as Recall, Precision, Precision at-10 and Recall at-10, that also point out that the proposed approach outperforms Lucene. Finally, another important contribution is a set of queries and WADL files gathered from Internet that can be used for evaluating future discovery proposals.