Rider-Rank Algorithm-Based Feature Extraction for Re-ranking the Webpages in the Search Engine

Abstract

AbstractThe webpage re-ranking is a challenging task while retrieving the webpages based on the query of the user. Even though the webpages in the search engines are ordered depends on the importance of the content, retrieving the necessary documents based on the input query is quite difficult. Hence, it is required to re-rank the webpages available in the websites based on the features of the pages in the search engines, like Google and Bing. Thus, an effective Rider-Rank algorithm is proposed to re-rank the webpages based on the Rider Optimization Algorithm (ROA). The input queries are forwarded to different search engines, and the webpages generated from the search engines with respect to the input query are gathered. Initially, the keywords are generated for the webpages. Then, the top keyword is selected, and the features are extracted from the top keyword using factor-based, text-based and rank-based features of the webpage. Finally, the webpages are re-ranked using the Rider-Rank algorithm. The performance of the proposed approach is analyzed based on the metrics, such as F-measure, recall and precision. From the analysis, it can be shown that the proposed algorithm obtains the F-measure, recall and precision of 0.90, 0.98 and 0.84, respectively.