Specificity-Aware Ontology Generation for Improving Web Service Clustering

Abstract

SUMMARYWith the expansion of the Internet, the number of available Web services has increased. Web service clustering to identify functionally similar clusters has become a major approach to the efficient discovery of suitable Web services. In this study, we propose a Web service clustering approach that uses novel ontology learning and a similarity calculation method based on the specificity of an ontology in a domain with respect to information theory. Instead of using traditional methods, we generate the ontology using a novel method that considers the specificity and similarity of terms. The specificity of a term describes the amount of domain-specific information contained in that term. Although general terms contain little domain-specific information, specific terms may contain much more domain-related information. The generated ontology is used in the similarity calculations. New logic-based filters are introduced for the similarity-calculation procedure. If similarity calculations using the specified filters fail, then information-retrieval-based methods are applied to the similarity calculations. Finally, an agglomerative clustering algorithm, based on the calculated similarity values, is used for the clustering. We achieved highly efficient and accurate results with this clustering approach, as measured by improved average precision, recall, Fmeasure, purity and entropy values. According to the results, specificity of terms plays a major role when classifying domain information. Our novel ontology-based clustering approach outperforms comparable existing approaches that do not consider the specificity of terms.

Alleviating sparsity by specificity‐aware ontology‐based clustering for improving web service recommendation

“…To alleviate the sparsity, there are several existing approaches as described in Sections 2.2.1 and 2.2.2. Alleviating sparsity using clustering‐based method is one of the existing methods and there are several existing approaches for clustering . Among those clustering approaches, our previously proposed ontology‐based clustering approach showed better results.…”

“…Among those clustering approaches, our previously proposed ontology‐based clustering approach showed better results. Our previous approach proposed only a clustering method and in this article, we use that clustering results to alleviate the sparsity problem in the user‐service dataset and then continue the process until improving the recommendation performance.…”

“…Based on the clustering performance, we mainly consider three approaches. The hybrid term similarity (HTS) method uses an ontology learning method for the similarity calculation and the agglomerative clustering algorithm for the clustering The context‐aware similarity (CAS) method uses a support vector machine for the similarity calculation and a spherical associated keyword space algorithm is applied to visualize the service clusters. In addition, our previously proposed clustering approach uses the novel specificity‐aware ontology generating method for the clustering. …”

“…However, the specificity of a term explains the quantity of domain‐specific information contained in the term, which is essential in generating a more efficient detailed hierarchy. Our proposed clustering approach takes advantage of this domain specificity. We selected the method to alleviate sparsity by evaluation of the high performance of the clustering results as well as the recommendation.…”

“…According to the ontology relationship of each term, we defined different machine filters and assigned weight values for each filter. The similarity calculation is performed by an edge count‐based method using an ontology relationship and assigned weight values .…”