Designing Effective Web Personalization for Knowledge Acquisition

Abstract

The World Wide Web (WWW) was developed in 1991 by Tim Berners-Lee from the newlineConseil European Pour Recherches Nucleaires (CERN). Since then www has come newlinea long way and has become one of the simple and popular way of transferring data. newlineThe World Wide Web has become one of the largest, fastest and most popular ways newlineof information sharing platform. Now days the www is the huge collection of newlineinformation that is gathered from various sources like web pages, web logs and the newlineusers access and this information is growing tremendously it is found by the newlineresearchers that more than 1.5 million pages are added every day. These pages are newlinenot structures and the information is also scattered therefore the finding the relevant newlineinformation is a typical task on the www. So the average user of the World Wide newlineWeb it is difficult to find the required information timely and appropriately. newlineHere come the applications of web personalization which solve the problem of newlinefinding the relevant information to the user. These system works on the information newlinecollected by them explicitly or implicitly from the usage of the web , web content, newlinesemantic of the web pages and the structure of the Web site. In order to achieve newlinemeet the specific needs of the individual users the content and the structure of the newlinewebsites are customized, without requiring the users to ask for it explicitly [1]. newlineThe Web personalization [1, 25, 27] is basically used as filter mechanism for a newlineparticular user, or a group of users [6]. The Web personalization works in newlinecombinations with several research fields like machine learning, information retrieval newline, Big data, social networks data base, data mining, Artificial Intelligence and newlinerecommender systems. newlineRecommender systems works on obtaining the relevant information for the user and newlinethe suggested actions, items, or decisions. These system works as extracting newlineinformation source to deal with the information overload. The first Recommender newlinesystems have been put among the researchers in the mid-1990s [34, 35].