Estimating Coverage of the Web Search Services Using Near-Uniform Sampling of Web Documents


The KIPS Transactions:PartD, Vol. 15, No. 3, pp. 305-312, Jun. 2008
10.3745/KIPSTD.2008.15.3.305,   PDF Download:

Abstract

Web documents with useful information are widely available on the internet and they are accessible with web search service. For this reason, web search services study better ways to collect more web documents, but have a difficulty figuring out the coverage of these web pages. This paper is intended to find ways to evaluate the current coverage assessment methods and suggest more effective coverage assessment technique that is, sampling internet web documents equally, monitoring how they are classified on web search services, in an attempt to assess both absolute and relative coverage of the web search engines. The paper also presents the comparison among Korean web search services using the suggested methods?the absolute and relative coverage was highest in Google followed by Naver and Empas. The result is expected to help estimating coverage of web search services.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
S. S. Jang, K. H. Kim, J. H. Lee, "Estimating Coverage of the Web Search Services Using Near-Uniform Sampling of Web Documents," The KIPS Transactions:PartD, vol. 15, no. 3, pp. 305-312, 2008. DOI: 10.3745/KIPSTD.2008.15.3.305.

[ACM Style]
Sung Soo Jang, Kwang Hyun Kim, and Joon Ho Lee. 2008. Estimating Coverage of the Web Search Services Using Near-Uniform Sampling of Web Documents. The KIPS Transactions:PartD, 15, 3, (2008), 305-312. DOI: 10.3745/KIPSTD.2008.15.3.305.