{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:31:48Z","timestamp":1780633908717,"version":"3.54.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,4,18]],"date-time":"2017-04-18T00:00:00Z","timestamp":1492473600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s00799-017-0215-9","type":"journal-article","created":{"date-parts":[[2017,4,18]],"date-time":"2017-04-18T12:55:09Z","timestamp":1492520109000},"page":"57-75","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Quantifying retrieval bias in Web archive search"],"prefix":"10.1007","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9872-5258","authenticated-orcid":false,"given":"Thaer","family":"Samar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Myriam C.","family":"Traub","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacco","family":"van Ossenbruggen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lynda","family":"Hardman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arjen P.","family":"de Vries","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2017,4,18]]},"reference":[{"key":"215_CR1","first-page":"1","volume":"11","author":"O Alonso","year":"2011","unstructured":"Alonso, O., Str\u00f6tgen, J., Baeza-Yates, R.A., Gertz, M.: Temporal information retrieval: challenges and opportunities. TWAW 11, 1\u20138 (2011)","journal-title":"TWAW"},{"key":"215_CR2","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., Bache, R.: On the relationship between effectiveness and accessibility. In: Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 889\u2013890. ACM (2010)","DOI":"10.1145\/1835449.1835667"},{"key":"215_CR3","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., de Rijke, M.: Automatic construction of known-item finding test beds. In: Proceedings of the 29th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR \u201906, pp. 603\u2013604. ACM, New York (2006)","DOI":"10.1145\/1148170.1148276"},{"key":"215_CR4","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., de Rijke, M., Balog, K.: Building simulated queries for known-item topics: an analysis using six European languages. In: SIGIR 2007: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Amsterdam, The Netherlands, July 23\u201327, 2007, pp. 455\u2013462 (2007)","DOI":"10.1145\/1277741.1277820"},{"key":"215_CR5","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., Vinay, V.: Accessibility in information retrieval. In: Proceedings of the Advances in Information Retrieval, 30th European Conference on IR Research, ECIR 2008, Glasgow, UK, March 30\u2013April 3, 2008, pp. 482\u2013489 (2008)","DOI":"10.1007\/978-3-540-78646-7_46"},{"key":"215_CR6","unstructured":"Azzopardi, L., Vinay, V.: Document accessibility: evaluating the access afforded to a document by the retrieval system. In: Workshop on Novel Methodologies for Evaluation in Information Retrieval, pp. 52\u201360. Citeseer (2008)"},{"key":"215_CR7","doi-asserted-by":"crossref","unstructured":"Azzopardi, L., Vinay, V.: Retrievability: an evaluation measure for higher order information access tasks. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, CIKM \u201908, pp. 561\u2013570. ACM, New York (2008)","DOI":"10.1145\/1458082.1458157"},{"key":"215_CR8","doi-asserted-by":"crossref","unstructured":"Bache, R., Azzopardi, L.: Improving access to large patent corpora. In: Transactions on Large-Scale Data-and Knowledge-Centered Systems II, pp. 103\u2013121. Springer (2010)","DOI":"10.1007\/978-3-642-16175-9_4"},{"key":"215_CR9","doi-asserted-by":"crossref","unstructured":"Bashir, S., Rauber, A.: Analyzing document retrievability in patent retrieval settings. In: International Conference on Database and Expert Systems Applications, pp.753\u2013760. Springer (2009)","DOI":"10.1007\/978-3-642-03573-9_63"},{"key":"215_CR10","doi-asserted-by":"crossref","unstructured":"Bashir, S., Rauber, A.: Improving retrievability of patents with cluster-based pseudo-relevance feedback documents selection. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 1863\u20131866. ACM (2009)","DOI":"10.1145\/1645953.1646250"},{"key":"215_CR11","doi-asserted-by":"crossref","unstructured":"Bashir, S., Rauber, A.: Improving retrievability of patents in prior-art search. In: European Conference on Information Retrieval, pp. 457\u2013470. Springer (2010)","DOI":"10.1007\/978-3-642-12275-0_40"},{"issue":"8","key":"215_CR12","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1002\/asi.21549","volume":"62","author":"S Bashir","year":"2011","unstructured":"Bashir, S., Rauber, A.: On the relationship between query characteristics and IR functions retrieval bias. J. Am. Soc. Inf. Sci. Technol. 62(8), 1515\u20131532 (2011)","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"issue":"1\u20132","key":"215_CR13","doi-asserted-by":"publisher","first-page":"93","DOI":"10.7227\/ALX.0022","volume":"25","author":"A Ben-David","year":"2014","unstructured":"Ben-David, A., Huurdeman, H.: Web archive search as research: methodological and theoretical implications. Alexandria 25(1\u20132), 93\u2013111 (2014)","journal-title":"Alexandria"},{"key":"215_CR14","doi-asserted-by":"crossref","unstructured":"Berberich, K., Bedathur, S., Alonso, O., Weikum, G.: A language modeling approach for temporal information needs. In: European Conference on Information Retrieval, pp. 13\u201325. Springer (2010)","DOI":"10.1007\/978-3-642-12275-0_5"},{"issue":"2","key":"215_CR15","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1145\/382979.383040","volume":"19","author":"J Callan","year":"2001","unstructured":"Callan, J., Connell, M.: Query-based sampling of text databases. ACM Trans. Inf. Syst. 19(2), 97\u2013130 (2001)","journal-title":"ACM Trans. Inf. Syst."},{"issue":"2","key":"215_CR16","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/2619088","volume":"47","author":"R Campos","year":"2015","unstructured":"Campos, R., Dias, G., Jorge, A.M., Jatowt, A.: Survey of temporal information retrieval and related applications. ACM Comput. Surv. 47(2), 15 (2015)","journal-title":"ACM Comput. Surv."},{"key":"215_CR17","doi-asserted-by":"crossref","unstructured":"Costa, M., Couto, F., Silva, M.: Learning temporal-dependent ranking models. In: Proceedings of the 37th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 757\u2013766. ACM (2014)","DOI":"10.1145\/2600428.2609619"},{"key":"215_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00799-015-0167-x","volume":"17","author":"M Costa","year":"2016","unstructured":"Costa, M., Gomes, D., Silva, M.J.: The evolution of web archiving. Int. J. Digit. Libr. 17, 1\u201315 (2016)","journal-title":"Int. J. Digit. Libr."},{"key":"215_CR19","unstructured":"Costa, M., Silva, M.J.: Understanding the information needs of web archive users. In: Proceedings of the 10th International Web Archiving Workshop, vol. 9, p. 6 (2010)"},{"key":"215_CR20","unstructured":"Costa, M., Silva, M.J.: Characterizing search behavior in web archives. In: WWW2011 Workshop on Linked Data on the Web, Hyderabad, India, March 29, 2011, pp. 33\u201340 (2011)"},{"key":"215_CR21","doi-asserted-by":"crossref","unstructured":"Costa, M., Silva, M.J.: Evaluating web archive search systems. In: Proceedings of the Web Information Systems Engineering\u2014WISE 2012-13th International Conference, Paphos, Cyprus, November 28\u201330, 2012, pp. 440\u2013454 (2012)","DOI":"10.1007\/978-3-642-35063-4_32"},{"key":"215_CR22","doi-asserted-by":"crossref","unstructured":"Craswell, N., Hawking, D., Robertson, S.: Effective site finding using link anchor information. In: SIGIR, pp. 250\u2013257. ACM (2001)","DOI":"10.1145\/383952.383999"},{"key":"215_CR23","doi-asserted-by":"crossref","unstructured":"Dou, Z., Song, R., Nie, J.-Y., Wen, J.R.: Using anchor texts with their hyperlink structure for web search. In: SIGIR, pp. 227\u2013234 (2009)","DOI":"10.1145\/1571941.1571982"},{"key":"215_CR24","doi-asserted-by":"crossref","unstructured":"Eiron, N., McCurley, K.S.: Analysis of anchor text for web search. In: SIGIR 2003: Proceedings of the 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, July 28\u2013August 1, 2003, Toronto, Canada, pp. 459\u2013460 (2003)","DOI":"10.1145\/860435.860550"},{"key":"215_CR25","doi-asserted-by":"crossref","unstructured":"Fujii, A.: Modeling anchor text and classifying queries to enhance web document retrieval. In: WWW, pp. 337\u2013346 (2008)","DOI":"10.1145\/1367497.1367544"},{"issue":"3","key":"215_CR26","doi-asserted-by":"publisher","first-page":"306","DOI":"10.2307\/1937992","volume":"54","author":"JL Gastwirth","year":"1972","unstructured":"Gastwirth, J.L.: The estimation of the lorenz curve and gini index. Rev. Econ. Stat. 54(3), 306\u2013316 (1972)","journal-title":"Rev. Econ. Stat."},{"key":"215_CR27","doi-asserted-by":"crossref","unstructured":"Gomes, D., Miranda, J., Costa, M.: A survey on web archiving initiatives. In: TPDL, pp. 408\u2013420 (2011)","DOI":"10.1007\/978-3-642-24469-8_41"},{"key":"215_CR28","unstructured":"Gomes, D., Nogueira, A., Miranda, J., Costa, M.:Introducing the Portuguese web archive initiative. In: 8th International Web Archiving Workshop. Springer (2009)"},{"issue":"3","key":"215_CR29","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1007\/s00799-015-0153-3","volume":"16","author":"HC Huurdeman","year":"2015","unstructured":"Huurdeman, H.C., Kamps, J., Samar, T., de Vries, A.P., Ben-David, A., Rogers, R.A.: Lost but not forgotten: finding pages on the unarchived web. Int. J. Digit. Libr. 16(3), 247\u2013265 (2015)","journal-title":"Int. J. Digit. Libr."},{"key":"215_CR30","doi-asserted-by":"crossref","unstructured":"Jin, R., Hauptmann, A.G., Zhai, C.: Title language model for information retrieval. In: SIGIR 2002: Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, August 11\u201315, 2002, Tampere, Finland, pp. 42\u201348 (2002)","DOI":"10.1145\/564376.564386"},{"key":"215_CR31","doi-asserted-by":"crossref","unstructured":"Kamps, J.: Web-centric language models. In: CIKM, pp. 307\u2013308 (2005)","DOI":"10.1145\/1099554.1099640"},{"issue":"2","key":"215_CR32","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1561\/1500000043","volume":"9","author":"N Kanhabua","year":"2015","unstructured":"Kanhabua, N., Blanco, R., N\u00f8rv\u00e5g, K.: Temporal information retrieval. Found. Trends Inf. Retr. 9(2), 91\u2013208 (2015)","journal-title":"Found. Trends Inf. Retr."},{"issue":"1\u20132","key":"215_CR33","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s00799-014-0108-0","volume":"14","author":"M Klein","year":"2014","unstructured":"Klein, M., Nelson, M.L.: Moved but not gone: an evaluation of real-time methods for discovering replacement web pages. Int. J. Digit. Libr. 14(1\u20132), 17\u201338 (2014)","journal-title":"Int. J. Digit. Libr."},{"key":"215_CR34","doi-asserted-by":"crossref","unstructured":"Kleinberg, J.M.: Authoritative sources in a hyperlinked environment. J. ACM 46(5), 604\u2013632 (1999)","DOI":"10.1145\/324133.324140"},{"key":"215_CR35","doi-asserted-by":"crossref","unstructured":"Koolen, M., Kamps, J.: The importance of anchor text for ad hoc search revisited. In: SIGIR, pp. 122\u2013129 (2010)","DOI":"10.1145\/1835449.1835472"},{"key":"215_CR36","doi-asserted-by":"crossref","unstructured":"Kraft, R., Zien, J.: Mining anchor text for query refinement. In: Proceedings of the 13th International Conference on World Wide Web, WWW, pp. 666\u2013674. ACM, New York (2004)","DOI":"10.1145\/988672.988763"},{"key":"215_CR37","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"CD Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Sch\u00fctze, H.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)"},{"key":"215_CR38","doi-asserted-by":"crossref","unstructured":"Metzler, D., Novak, J., Cui, H., Reddy, S.: Building enriched document representations using aggregated anchor text. In: SIGIR (2009)","DOI":"10.1145\/1571941.1571981"},{"key":"215_CR39","unstructured":"Page, L., Brin, S., Motwani, R., Winograd, T.: The PageRank citation ranking: bringing order to the web. Technical Report 1999-66, Stanford InfoLab, November 1999. Previous number $$=$$ = SIDL-WP-1999-0120"},{"key":"215_CR40","unstructured":"Ras, M.: Eerste fase webarchivering. Technical Report, Koninklijke Bibliotheek (2007)"},{"key":"215_CR41","unstructured":"Ras, M., van Bussel, S.: Web archiving user survey. Technical Report, National Library of the Netherlands (Koninklijke Bibliotheek). https:\/\/www.kb.nl\/sites\/default\/files\/KB_UserSurvey_Webarchive_EN.pdf (2007)"},{"key":"215_CR42","doi-asserted-by":"crossref","unstructured":"Rauber, A., Bruckner, R.M., Aschenbrenner, A., Witvoet, O., Kaiser, M.: Uncovering information hidden in web archives: a glimpse at web analysis building on data warehouses. D-Lib Mag. 8(12). http:\/\/www.dlib.org\/dlib\/december02\/rauber\/12rauber.html (2002)","DOI":"10.1045\/december2002-rauber"},{"key":"215_CR43","doi-asserted-by":"crossref","unstructured":"Traub, M.C., Samar, T., van Ossenbruggen, J., He, J., de Vries, A., Hardman, L.: Querylog-based assessment of retrievability bias in a large newspaper corpus. In: Proceedings of the 16th ACM\/IEEE-CS on Joint Conference on Digital Libraries, pp. 7\u201316. ACM (2016)","DOI":"10.1145\/2910896.2910907"},{"key":"215_CR44","doi-asserted-by":"crossref","unstructured":"Wilkie, C., Azzopardi, L.: Relating retrievability, performance and length. In: Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 937\u2013940. ACM (2013)","DOI":"10.1145\/2484028.2484145"}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00799-017-0215-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-017-0215-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-017-0215-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,5]],"date-time":"2020-10-05T18:21:34Z","timestamp":1601922094000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00799-017-0215-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,18]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["215"],"URL":"https:\/\/doi.org\/10.1007\/s00799-017-0215-9","relation":{},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"value":"1432-5012","type":"print"},{"value":"1432-1300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4,18]]},"assertion":[{"value":"1 March 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 March 2017","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2017","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}