{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:22:10Z","timestamp":1775744530128,"version":"3.50.1"},"reference-count":33,"publisher":"Elsevier BV","issue":"6","license":[{"start":{"date-parts":[[2003,11,1]],"date-time":"2003-11-01T00:00:00Z","timestamp":1067644800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2003,11]]},"DOI":"10.1016\/s0306-4573(02)00084-5","type":"journal-article","created":{"date-parts":[[2003,5,12]],"date-time":"2003-05-12T23:55:41Z","timestamp":1052783741000},"page":"853-871","source":"Crossref","is-referenced-by-count":94,"title":["Engineering a multi-purpose test collection for Web retrieval experiments"],"prefix":"10.1016","volume":"39","author":[{"given":"Peter","family":"Bailey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nick","family":"Craswell","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Hawking","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0306-4573(02)00084-5_BIB1","unstructured":"Alis Technology Inc. (2001). ?\u2019qu\u00e9? system for identification of language and character encoding. Available: www.alis.com\/castil\/silc\/. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB2","unstructured":"Bailey, P., Craswell, N., & Hawking, D. (2000). Dark matter on the web. In WWW9 Poster Proceedings. Available: www.www9.org\/final-posters\/poster30.html. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB3","unstructured":"Bharat, K., Broder, A., Dean, J., & Henzinger, M. (1999). A comparison of techniques to find mirrored hosts on the WWW. In Proceedings of the ACM Digital Libraries \u201999 Workshop on Organizing Web Space (WOWS), Berkeley, CA. Available: research.microsoft.com\/research\/db\/debull\/A00dec\/bharat.ps. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB4","doi-asserted-by":"crossref","unstructured":"Brin, S., & Page, L. (1998). The anatomy of a large-scale hypertextual Web search engine. In Proceedings of the seventh international world wide web conference, pp. 107\u2013118","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB5","doi-asserted-by":"crossref","unstructured":"Broder, A., Kumar, R., Maghoul, F., Raghavan, P., Rajagopalan, S., Stata, R., Tomkins, A., & Wiener, J. (2000). Graph structure in the web. In Proceedings of WWW9, Amsterdam. Available: www9.org\/w9cdrom\/contents.html#CHARACTERIZATION. Accessed 20 Aug 2002","DOI":"10.1016\/S1389-1286(00)00083-9"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB6","series-title":"Readings in information retrieval","first-page":"47","article-title":"The Cranfield tests on index language devices","author":"Cleverdon","year":"1997"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB7","doi-asserted-by":"crossref","unstructured":"Craswell, N., Hawking, D., & Robertson, S. (2001). Effective site finding using link anchor information. In Proceedings of ACM SIGIR 2001, New Orleans, pp. 250\u2013257. Available: www.ted.cmis.csiro.au\/~nickc\/pubs\/sigir01.pdf","DOI":"10.1145\/383952.383999"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB8","unstructured":"CSIRO (2001). TREC Web Tracks homepage. Available: www.ted.cmis.csiro.au\/TRECWeb\/"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB9","doi-asserted-by":"crossref","unstructured":"Faloutsos, M., Faloutsos, P., & Faloutsos, C. (1999). On power-law relationships of the internet topology. In Proceedings of ACM SIGCOMM\u201999, pp. 251\u2013262","DOI":"10.1145\/316188.316229"},{"issue":"2","key":"10.1016\/S0306-4573(02)00084-5_BIB10","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/S0306-4573(98)00041-7","article-title":"Finding information on the world wide web: The retrieval effectiveness of search engines","volume":"35","author":"Gordon","year":"1999","journal-title":"Information Processing and Management"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB11","series-title":"Readings in information retrieval","first-page":"247","article-title":"The TREC Conferences","author":"Harman","year":"1997"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB12","unstructured":"Hawking, D., & Craswell, N. (2001). Overview of the TREC-2001 Web Track. In Proceedings of TREC-2001, Gaithersburg MD. NIST special publication 500-250. Available: trec.nist.gov"},{"issue":"1","key":"10.1016\/S0306-4573(02)00084-5_BIB13","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1023\/A:1011468107287","article-title":"Measuring search engine quality","volume":"4","author":"Hawking","year":"2001","journal-title":"Information Retrieval"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB14","unstructured":"Hawking, D., Craswell, N., & Thistlewaite, P. (1998). Overview of the TREC-7 very large collection track. In Proceedings of TREC-7, Gaithersburg, MD, NIST, pp. 91\u2013104"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB15","unstructured":"Hawking, D., & Thistlewaite, P. (1997). Overview of the TREC-6 very large collection track. In Proceedings of TREC-6, Gaithersburg, MD. NIST"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB16","unstructured":"Hawking, D., Thistlewaite, P., & Craswell, N. (1997). ANU\/ACSys TREC-6 experiments. In Proceedings of TREC-6, Gaithersburg, MD, NIST, pp. 275\u2013290"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB17","unstructured":"Hawking, D., Voorhees, E., Bailey, P., & Craswell, N. (2000). Overview of the TREC-9 web track. In Proceedings of TREC-9, Gaithersburg MD, NIST special publication 500-249. Available: trec.nist.gov"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB18","unstructured":"Hawking, D., Voorhees, E., Craswell, N., & Bailey, P. (1999). Overview of the TREC-8 web track. In Proceedings of TREC-8, Gaithersburg, MD, NIST, pp. 131\u2013150"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB19","series-title":"Statistics","author":"Hays","year":"1963"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB20","doi-asserted-by":"crossref","unstructured":"Henzinger, M.R., Heydon, A., Mitzenmacher, M., & Najork, M. (1999). Measuring index quality using random walks on the web. In Proceedings of WWW8, Toronto. Available: www8.org\/w8-papers\/2c-search-discover\/measuring\/measuring.html","DOI":"10.1016\/S1389-1286(99)00016-X"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB21","doi-asserted-by":"crossref","unstructured":"Henzinger, M.R., Heydon, A., Mitzenmacher, M., & Najork, M. (2000). On near-uniform url sampling. In Proceedings of WWW9, Amsterdam. Available: www9.org\/w9cdrom\/contents.html#Characterization. Accessed 20 Aug 2002","DOI":"10.1016\/S1389-1286(00)00055-4"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB22","unstructured":"Huberman, B.A., & Adamic, L.A. (1999). Evolutionary dynamics of the World Wide Web. Available: www.hpl.hp.com\/shl\/papers\/webgrowth\/. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB23","unstructured":"Internet Archive (1997). Building a digital library for the future. Available: www.archive.org\/. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB24","unstructured":"Kleinberg, J. (1997). Authoritative sources in a hyperlinked environment. Technical Report RJ 10076, IBM"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB25","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1038\/21987","article-title":"Accessiblity and distribution of information on the Web","volume":"400","author":"Lawrence","year":"1999","journal-title":"Nature"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB26","unstructured":"NIST (2001). Trec home page. Available: trec.nist.gov\/. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB27","unstructured":"O\u2019Neill, E., Lavoie, B., & McClain, P. (1998). OCLC web characterization project. In Report of the W3C web characterization group conference, Cambridge, MA. Available: www.w3.org\/1998\/11\/05\/WC-workshop\/Papers\/oneill.htm. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB28","doi-asserted-by":"crossref","unstructured":"Robertson, S.E., Walker, S., Hancock-Beaulieu, M., & Gatford, M. (1994). Okapi at TREC-3. In Proceedings of TREC-3, Gaithersburg, MD, NIST","DOI":"10.6028\/NIST.SP.500-225.city"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB29","unstructured":"Savoy, J., & Rasolofo, Y. (2000). Report on the TREC-9 experiment: Link-based retrieval and distributed collections. In Proceedings of TREC-9, Gaithersburg, MD, NIST, pp. 579\u2013588. Available: trec.nist.gov"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB30","unstructured":"Savoy, J., & Rasolofo, Y. (2001). Report on the TREC-10 experiment: Distributed collections and entrypage searching. In Proceedings of TREC-2001, Gaithersburg, MD, NIST, pp. 586\u2013595. Available: trec.nist.gov"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB31","unstructured":"The World Wide Web Consortium (1998). Available: www.w3c.org.. Accessed 20 Aug 2002"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB32","doi-asserted-by":"crossref","unstructured":"Voorhees, E. (2001). Evaluation by highly relevant documents. In Proceedings of SIGIR\u201901, New Orleans, LA, pp. 74\u201382","DOI":"10.1145\/383952.383963"},{"key":"10.1016\/S0306-4573(02)00084-5_BIB33","unstructured":"Westerveld, T., Kraaij, W., & Hiemstra, D. (2001). Retrieving web pages using content, links, urls and anchors. In Proceedings of TREC-2001, Gaithersburg, MD, NIST, pages 663\u2013672. Available: trec.nist.gov"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457302000845?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457302000845?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T16:29:45Z","timestamp":1734020985000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457302000845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,11]]},"references-count":33,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2003,11]]}},"alternative-id":["S0306457302000845"],"URL":"https:\/\/doi.org\/10.1016\/s0306-4573(02)00084-5","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2003,11]]}}}