Improved Fuzzy Rank Aggregation

Abstract

Rank aggregation is applied on the web to build various applications like meta-search engines, consumer reviews classification, and recommender systems. Meta-searching is the generation of a single list from a collection of the results produced by multiple search engines, together using a rank aggregation technique. It is an efficient and cost-effective technique to retrieve quality results from the internet. The quality of results produced by a meta-searching relies upon the efficiency of rank aggregation technique applied. An effective rank aggregation technique assigns the rank to a document that is closest to all its previous rankings. The newly generated list of documents may be evaluated by the measurement of Spearman footrule distance. In this article, various fuzzy logic techniques for rank aggregation are analyzed and further improvements are proposed in Modified Shimura technique. Consequently, two novel OWA operators are suggested for the calculation of membership values of document ranks in a modified Shimura technique. The performance of proposed improvements is evaluated on the Spearman footrule distance along with execution time. The results show that the anticipated improvements exhibit better performance than other fuzzy techniques.