Abstract

Background: Clustering is one of the important techniques in Data Mining to group the related data. Clustering can be applied to numerical data as well as web objects such as URLs, websites, documents, keywords, etc. which is the building block for many recommender systems as well as prediction models.

Objective: The objective of this research article is to develop an optimal clustering approach, which considers the semantics of web objects to cluster them in a group. More so importantly, the purpose of the proposed work is to strictly improve the computation time of the clustering process.

Methods: In order to achieve the desired objectives, the following two contributions have been proposed to improve the clustering approach 1) Semantic Similarity Measure based on Wu-Palmer Semantics- based similarity and 2)Two-Level Density-based Clustering technique to reduce the computational complexity of density-based clustering approach.

Results: The efficacy of the proposed method has been analyzed on AOL search logs containing 20 million web queries. The results showed that our approach increases the F-measure, and decreases the entropy. It also reduces the computational complexity and provides a competitive alternative strategy of semantic clustering when conventional methods do not provide helpful suggestions.

Conclusion: A clustering model has been proposed, which is composed of two components, i.e., similarity measure and Density-based two-level clustering technique. The proposed model reduced the time cost of the density-based clustering approach without effecting the performance.

Keywords: Semantic clustering, similarity measure, entropy, f-measure, ontology, and density-based clustering.

Graphical Abstract