(cache)Similarity based Automatic Web Search Engine Evaluation | IEEE Conference Publication | IEEE Xplore

Similarity based Automatic Web Search Engine Evaluation


Abstract:

Nowadays, as the usage of Internet has incredibly increased, web search engines become the common approach to find and retrieve needed information. Hence, evaluating sear...Show More

Abstract:

Nowadays, as the usage of Internet has incredibly increased, web search engines become the common approach to find and retrieve needed information. Hence, evaluating search engine quality is a hot topic which attracts many researches' attention. In this paper, we propose a framework named Similarity based Automatic Web Search Engine Evaluation, SAWSEE, to evaluate web search engines. SAWSEE measures the information retrieval effectiveness of web search engines by comparing and voting their returned results, particularly using nDCG metric to rank search engines. SAWSEE compares the search engines' results based on their similarity which is calculated in two consecutive levels, the web page address level and the main content of web page level. To find the similarity of the main content of two search engines' results, SAWSEE utilizes Winnowing algorithm, a well-known and widely-used plagiarism detection method. We compared our method with the results acquired from human assessors' evaluations. The promising comparison shows that SAWSEE provides rankings that are consistent with the rankings resulted from human assessors' evaluations. Hence, the proposed method can be applied in real world environments for evaluation of web search engines.
Date of Conference: 27-28 September 2016
Date Added to IEEE Xplore: 20 March 2017
ISBN Information:
Conference Location: Tehran, Iran

I. Introduction

Search engines are the main gateway to the Web. This subject represents the importance of the evaluation of search engine. The most important factor in user satisfaction of search engine, is the relevance of the results provided by it which is measured by precision factor. To the best of our knowledge, the proposed methods in the literature for precision estimation could be seen from different viewpoints. Because a search engine must show a ranked list of results in response to the queries which has be send from user to it. As the documents were returned in the top of the list have the better quality the search engine has the higher precision which is measured by evaluation methods. According to the judgment agent, the evaluation methods could be categorized to automatic evaluation methods [21] [3] and human based evaluation methods [2] [22]–[24]. In fact, an evaluation system consists of three main parts which are the query generation unit, the judgment unit and the unit for criteria computation. The judgment unit is the most important and most expensive part of the evaluation system. Automatic or human based evaluation is related to the implementation of the judgment unit.

Contact IEEE to Subscribe

References

References is not available for this document.