An Effective Web Page Personalization model using Weighted Clustering and Improved Whale Optimization Algorithm

Abstract

Web page personalization is the procedure of customizing a web page based on the requirements of every particular user or a group of users by utilizing the knowledge attained from the investigation of user’s navigational actions. Personalized recommendation predicts the browsing nature of the user by the use of data mining techniques received significant interest in the domain of web personalization research area. This paper presents a clustering with similarity measure based web page personalization model. Here, the web page personalization takes place by formulating queries and profiling by the WordNet ontology. To begin with, the needed data is gathered from various web sources and are grouped by the use of Weighted Clustering (WC) technique. The WC groups the web pages with respect to the fields which are learned by the user learning process. Using the set of four similarity metrics, data resemblance will be computed among the created word net and trained dataset. Among them, the highest resemblance based data is offered by the Improved Whale Optimization algorithm (WOA), where the WOA algorithm is extended by the concept of tumbling effect. A series of simulations were carried out to highlight the betterment of the presented model under various aspects.