Finding information on the World Wide Web: the retrieval effectiveness of search engines

Gordon, Michael D.; Pathak, Praveen

doi:10.1016/s0306-4573(98)00041-7

Cited by 255 publications

(175 citation statements)

References 5 publications

Supporting

Mentioning

167

Contrasting

Unclassified

Order By: Relevance

“…Precision is the proportion of relevant items among those retrieved. In Gordon & Pathak (1999) precision within the top ten varied from 40.6% to17.6%, whereas in Chu & Rosenthal (1996) the range was from 78 % to 55 %. In a more recent study precision within the top 20 varied from 49 % to 34 % (Lewandowski 2008).…”

Section: Evaluation Of Search Enginesmentioning

confidence: 95%

See 1 more Smart Citation

Comparing Google to Ask-a-Librarian Service for Answering Factual and Topical Questions

Vakkari

Taneli

2009

Research and Advanced Technology for Digital Libraries

View full text Add to dashboard Cite

Abstract. This paper evaluates to which extent Google retrieved correct answers as responses to queries inferred from factual and topical requests in a digital Ask-a-Librarian service. 100 factual and 100 topical questions were picked from a digital reference service run by public libraries. The queries inferred simulated average Web queries. The top 10 retrieval results were observed for the answer. The inspection was stopped when the first correct answer was identified. Google retrieved correct answers to 42 % of the topical questions and 29 % of factual questions. Results concerning the characteristics of queries and retrieval effectiveness are also presented. Evaluations indicate that public libraries' reference services answer correctly 55 % of the questions. Thus, Google is not outperforming Ask-a-Librarian service, although it seems to perform relatively satisfactory in retrieving answers to topical questions.

show abstract

Section: Evaluation Of Search Enginesmentioning

confidence: 95%

“…The major studies in the 1990s (Chu & Rosenthal 1996, Gordon & Pathak 1999, Leighton & Srivastava 1999 have used queries drawn from real reference questions. The number of queries used is small varying in those studies from 5 to 15.…”

Section: Evaluation Of Search Enginesmentioning

confidence: 99%

Comparing Google to Ask-a-Librarian Service for Answering Factual and Topical Questions

Vakkari

Taneli

2009

Research and Advanced Technology for Digital Libraries

View full text Add to dashboard Cite

show abstract

“…Studies discussing the overlap of search results from different engines were conducted to a large extent. We will not discuss in detail earlier studies (Chignell et al 1999;Gordon and Pathak 1999;Nicholson 2000;Schwartz 1998). These all find little overlap between the Web search engines' results, but these findings are now of limited use because of the constantly changing Web search engine landscape.…”

Section: Uniqueness Of Search Resultsmentioning

confidence: 93%

‘Googling’ Terrorists: Are Northern Irish Terrorists Visible on Internet Search Engines?

Reilly

2008

Web Search

View full text Add to dashboard Cite

SummaryThe purpose of this paper is to describe various quality measures for search engines and to ask whether these are suitable. We especially focus on user needs and their use of Web search engines. The paper presents an extensive literature review and a first quality measurement model, as well. Findings include that Web search engine quality can not be measured by just retrieval effectiveness (the quality of the results), but should also consider index quality, the quality of the search features and Web search engine usability . For each of these sections, empirical results from studies conducted in the past, as well as from our own research are presented. These results have implications for the evaluation of Web search engines and for the development of better search systems that give the user the best possible search experience. IntroductionWeb search engines have become important for information seeking in many different contexts (e.g., personal, business, and scientific). Research questions not answered satisfactorily are, as of now, how well these engines perform regarding user expectations and what measures should be used to get an overall picture of search engine quality . It is well known that search engine quality in its entirety cannot be measured with the use of traditional retrieval measures. But the development of new, search engine specific measures, as proposed in Vaughan (2004) are not sufficient, either. Search engine quality must be defined more extensively and integrate factors beyond retrieval performance such as index quality and the quality of the search features.One aspect neglected is the user himself. But to discuss and judge the quality of search engines, it is important to focus on the user of such systems, too. Better performance of ranking algorithms or providing additional services does not always lead to users' satisfaction and to better search results. We focus on the Web search engine user behaviour to derive strategies to measure Web search engine quality . Additionally, quality assurance is an important aspect to improve customer satisfaction and loyalty. This is fundamental to protect market shares and revenues from

show abstract

“…A four level relevancy scale is used in this study, denoting relevancy levels of highly relevant (4), somewhat relevant (3), somewhat irrelevant (2) and highly irrelevant (1). A relevancy scale with four levels is used in prominent studies such as Gordon and Pathak (1999).…”

Section: The Relevance Evaluatormentioning

confidence: 99%

An architecture for SCS: A specialized web crawler on the topic of security

Özmutlu

Ozmutlu

2004

Proc of Assoc for Info

View full text Add to dashboard Cite

Mining for correct and relevant information in the World Wide Web is a difficult task, handled by Web crawlers. This study outlines the components of a specialized crawler on the topic of security (SCS) that heavily makes use of artificial neural networks and rule-based expert systems to establish successful focused crawling on the topic of security. SCS is designed to find, index and follow the updates of Web pages of interest, and proposes new approaches for reaching relevant pages, which might stay hidden to other crawling approaches. SCS consists of four new page explorers, a database of relevant pages, a relevance evaluator using artificial neural networks and an updater using rule-based expert systems. SCS is a multi-threaded multi-object Java Applet and Application combination with embedded SQL and PHP elements and is applicable on single or multiple machines through parallel processing with its expandable and modular structure.

show abstract

Finding information on the World Wide Web: the retrieval effectiveness of search engines

Cited by 255 publications

References 5 publications

Comparing Google to Ask-a-Librarian Service for Answering Factual and Topical Questions

Comparing Google to Ask-a-Librarian Service for Answering Factual and Topical Questions

‘Googling’ Terrorists: Are Northern Irish Terrorists Visible on Internet Search Engines?

An architecture for SCS: A specialized web crawler on the topic of security

Contact Info

Product

Resources

About