Abstract
Search engines are widely used for surfing the Internet. Different search engines vary with respect to their accuracy and time to fetch the information from the distributed/centralized database repository across the globe. However, it has been found in the literature that webpage ranking helps in saving the user's surfing time which in turn saves considerable energy consumption during computation and transmission across the network. Most of the earlier solutions reported in the literature uses the hyperlink structure of graph which consume a lot of energy during the computation. It may lead to the link leakage problem with the occurrence of spam pages more often. Nowadays, hyperlink structure alone is inadequate for predicting webpage importance keeping in view of the energy consumption of various smart devices. User browsing behavior depicts its real importance. It is essential to demote the spam pages to increase the search engine accuracy and speed. Hence, user behavior analysis along with demotion of spam pages can improve Search Engine Result Pages (SERP) which in turn saves the energy consumption. In the proposed approach, web page importance score is computed by analyzing user surfing behavior attributes, dwell time, and click count. After computing the webpage importance score, the ranks are revised by implementing it in Learning Automata (LA) environment. Learning automaton is the stochastic system which learns from the environment and responds either with a reward or a penalty. With every response from the environment, the probability of visiting the webpage is updated. Probability computation is done using Normal and Gamma distribution functions. In the proposal, we have considered only the dangling pages for experiments. Inactive webpages are punished and degraded from the system. We have validated proposed approach with Microsoft Learning to Rank dataset. It has been found in the experiments performed that 3403 dangling pages out of 12211 dangling pages have been degraded using the proposed scheme. The objective of the proposed scheme is achieved by saving web energy and computational cost. It takes 100 iterations to convergence which executed in 21.88 ms. However, the user behavior analysis helped in improving PageRank score of the webpages. (C) 2018 Elsevier Inc. All rights reserved.