Search Engines Evaluation

Abstract

The volume of world wide web (WWW) is increasing enormously due to a world wide move to migrate information to online sources. To search some information on WWW, search engines are used, which when presented with queries, return a list of web pages ranked on the basis of estimation of relevance. Generally the search engines due to the abundance of information available on the web return millions of pages. But user studies indicate that a common user browses through top 10 or 20 documents only. So it’s all-important to get into those top 10 documents. To achieve this web authors are increasingly beginning to rely on underhand techniques to ensure their sites get seen, in turn affecting the performance of search engines. The existing measures to evaluate these systems’ performance are not adequate in the current world of highly interactive end-user systems. In this study a metric 'Ranked Precision' is proposed to evaluate the performance of search engines.

http://dx.doi.org/10.14429/dbit.25.2.3649