{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T19:48:36Z","timestamp":1725652116109},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2015,11,13]],"date-time":"2015-11-13T00:00:00Z","timestamp":1447372800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2015,11,13]],"date-time":"2015-11-13T00:00:00Z","timestamp":1447372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Inf Retrieval J"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s10791-015-9275-x","type":"journal-article","created":{"date-parts":[[2015,11,13]],"date-time":"2015-11-13T13:49:47Z","timestamp":1447422587000},"page":"284-312","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Predicting relevance based on assessor disagreement: analysis and practical applications for search evaluation"],"prefix":"10.1007","volume":"19","author":[{"given":"Thomas","family":"Demeester","sequence":"first","affiliation":[]},{"given":"Robin","family":"Aly","sequence":"additional","affiliation":[]},{"given":"Djoerd","family":"Hiemstra","sequence":"additional","affiliation":[]},{"given":"Dong","family":"Nguyen","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Develder","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,11,13]]},"reference":[{"key":"9275_CR1","doi-asserted-by":"publisher","unstructured":"Agrawal, R., Gollapudi, S., Halverson, A., & Ieong, S. (2009). Diversifying search results. In Proceedings of the 2nd ACM international conference on web search and data mining (WSDM 2009) (pp. 5\u201314), Barcelona. doi:10.1145\/1498759.1498766.","DOI":"10.1145\/1498759.1498766"},{"key":"9275_CR2","doi-asserted-by":"publisher","unstructured":"Al-Harbi, A. L., & Smucker, M. D. (2014). A qualitative exploration of secondary assessor relevance judging behavior categories and subject descriptors. In Proceedings of the 5th information interaction in context symposium (IIiX 2014) (pp. 195\u2013204), Regensburg. doi:10.1145\/2637002.2637025.","DOI":"10.1145\/2637002.2637025"},{"key":"9275_CR3","doi-asserted-by":"publisher","unstructured":"Bailey, P., Craswell, N., Soboroff, I., & Thomas, P. (2008). Relevance assessment: Are judges exchangeable and does it matter? In Proceedings of the 31st international ACM SIGIR conference research and development in information retrieval (SIGIR 2008), Singapore. doi:10.1145\/1390334.1390447.","DOI":"10.1145\/1390334.1390447"},{"key":"9275_CR4","doi-asserted-by":"publisher","unstructured":"Carterette, B., & Soboroff, I. (2010). The effect of assessor errors on IR system evaluation. In Proceedings of the 33rd international ACM SIGIR conference on research and development in information retrieval (SIGIR 2010) (pp. 539\u2013546), Geneva. doi:10.1145\/1835449.1835540.","DOI":"10.1145\/1835449.1835540"},{"key":"9275_CR5","doi-asserted-by":"crossref","unstructured":"Carterette, B., Bennett, P. N., Chickering, D. M., & Dumais, S. T. (2008). Here or there: Preference judgments for relevance. In Proceedngs of the 30th European conference on advances in information retrieval (ECIR 2008) (pp. 16\u201327). Berlin: Springer.","DOI":"10.1007\/978-3-540-78646-7_5"},{"key":"9275_CR6","doi-asserted-by":"publisher","unstructured":"Carterette, B., Kanoulas, E., & Yilmaz, E. (2012). Incorporating variability in user behavior into systems based evaluation. In Proceedings of the 21st ACM international conference on information and knowledge management (CIKM\u201912) (pp. 135\u2013144). New York, NY: ACM. doi:10.1145\/2396761.2396782.","DOI":"10.1145\/2396761.2396782"},{"key":"9275_CR7","doi-asserted-by":"publisher","unstructured":"Chapelle, O., Metlzer, D., Zhang, Y., & Grinspan, P. (2009). Expected reciprocal rank for graded relevance. In Proceedings of the 18th ACM International Conference on Information and Knowledge Management (CIKM 2009) (pp. 621\u2013630), New York, NY. doi:10.1145\/1645953.1646033.","DOI":"10.1145\/1645953.1646033"},{"key":"9275_CR8","unstructured":"Demeester, T., Trieschnigg, D., Nguyen, D., & Hiemstra, D. (2013). Overview of the trec 2013 federated web search track. In Proceedings of the 22nd text retrieval conference (TREC 2013), Gaithersburg, MD."},{"key":"9275_CR9","doi-asserted-by":"publisher","unstructured":"Demeester, T., Aly, R., Hiemstra, D., Nguyen, D., Trieschnigg, D., & Develder, C. (2014). Exploiting user disagreement for web search evaluation: An experimental approach. In Proceedings of the 7th ACM international conference on web search and data mining (WSDM 2014) (pp. 33\u201342), New York, NY. doi:10.1145\/2556195.2556268.","DOI":"10.1145\/2556195.2556268"},{"key":"9275_CR10","doi-asserted-by":"publisher","unstructured":"Demeester, T., Trieschnigg, D., Zhou, K., Nguyen, D., & Hiemstra, D. (2015). FedWeb greatest hits: Presenting the new test collection for federated web search. In Proceedings of the 24th international world wide web conference (WWW 2015), Florence. doi:10.1145\/2740908.2742755.","DOI":"10.1145\/2740908.2742755"},{"issue":"1","key":"9275_CR11","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1002\/(SICI)1097-4571(199601)47:1<37::AID-ASI4>3.0.CO;2-3","volume":"47","author":"SP Harter","year":"1996","unstructured":"Harter, S. P. (1996). Variations in relevance assessments and the measurement of retrieval effectiveness. Journal of the American Society for Information Science, 47(1), 37\u201349. doi:10.1002\/(SICI)1097-4571(199601)47:1<3.0.CO;2-3.","journal-title":"Journal of the American Society for Information Science"},{"key":"9275_CR12","doi-asserted-by":"crossref","unstructured":"Hosseini, M., Cox, I. J., Mili\u0107-frayling, N., Kazai, G., & Vinay, V. (2012). On aggregating labels from multiple crowd workers to infer relevance of documents. In Proceedings of the 34th European conference on advances in information retrieval (ECIR 2012) (pp. 182\u2013194), Barcelona.","DOI":"10.1007\/978-3-642-28997-2_16"},{"issue":"4","key":"9275_CR13","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1145\/582415.582418","volume":"20","author":"K J\u00e4rvelin","year":"2002","unstructured":"J\u00e4rvelin, K., & Kek\u00e4l\u00e4inen, J. (2002). Cumulated gain-based evaluation of IR techniques. ACM Transactions on Information Systems, 20(4), 422\u2013446. doi:10.1145\/582415.582418.","journal-title":"ACM Transactions on Information Systems"},{"key":"9275_CR14","doi-asserted-by":"publisher","unstructured":"Kanoulas, E., & Aslam, J. A. (2009). Empirical justification of the gain and discount function for nDCG. In Proceedings of the 18th ACM international conference on information and knowledge management (CIKM 2009) (pp. 611\u2013620), Hong Kong. doi:10.1145\/1645953.1646032.","DOI":"10.1145\/1645953.1646032"},{"key":"9275_CR15","doi-asserted-by":"publisher","unstructured":"Kazai, G., Yilmaz, E., Craswell, N., & Tahaghoghi, S. (2013). User intent and assessor disagreement in web search evaluation. In Proceedings of the 22nd ACM international conference on conference on information and knowledge management (CIKM 2013) (pp. 699\u2013708). New York, NY: ACM. doi:10.1145\/2505515.2505716.","DOI":"10.1145\/2505515.2505716"},{"issue":"5","key":"9275_CR16","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1016\/j.ipm.2005.01.004","volume":"41","author":"J Kek\u00e4l\u00e4inen","year":"2005","unstructured":"Kek\u00e4l\u00e4inen, J. (2005). Binary and graded relevance in IR evaluations: Comparison of the effects on ranking of IR systems. Information Processing & Management, 41(5), 1019\u20131033. doi:10.1016\/j.ipm.2005.01.004.","journal-title":"Information Processing & Management"},{"issue":"1","key":"9275_CR17","doi-asserted-by":"publisher","first-page":"2:1","DOI":"10.1145\/1416950.1416952","volume":"27","author":"A Moffat","year":"2008","unstructured":"Moffat, A., & Zobel, J. (2008). Rank-biased precision for measurement of retrieval effectiveness. ACM Transactions on Information Systems, 27(1), 2:1\u20132:27. doi:10.1145\/1416950.1416952.","journal-title":"ACM Transactions on Information Systems"},{"key":"9275_CR18","doi-asserted-by":"publisher","unstructured":"Nguyen, D., Demeester, T., Trieschnigg, D., & Hiemstra, D. (2012). Federated search in the wild: The combined power of over a hundred search engines. In Proceedings of the 21st ACM international conference on information and knowledge management (CIKM 2012), Maui, HI. doi:10.1145\/2396761.2398535.","DOI":"10.1145\/2396761.2398535"},{"key":"9275_CR19","doi-asserted-by":"publisher","unstructured":"Robertson, S. E., Kanoulas, E., & Yilmaz, E. (2010). Extending average precision to graded relevance judgments. In Proceedings of the 33rd international ACM SIGIR conference on research and development in information retrieval (SIGIR 2010) (pp. 603\u2013610), Geneva. doi:10.1145\/1835449.1835550.","DOI":"10.1145\/1835449.1835550"},{"issue":"2","key":"9275_CR20","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1016\/j.ipm.2006.07.020","volume":"43","author":"T Sakai","year":"2007","unstructured":"Sakai, T. (2007). On the reliability of information retrieval metrics based on graded relevance. Information Processing & Management, 43(2), 531\u2013548. doi:10.1016\/j.ipm.2006.07.020.","journal-title":"Information Processing & Management"},{"key":"9275_CR21","doi-asserted-by":"crossref","unstructured":"Sakai, T., Dou, Z., Yamamoto, T., Liu, Y., Zhang, M., & Song, R. (2013). Overview of the NTCIR-10 INTENT-2 task. In Proceedings of the 10th NTCIR conference (pp. 94\u2013123), Tokyo.","DOI":"10.1145\/2484028.2484104"},{"key":"9275_CR22","doi-asserted-by":"publisher","unstructured":"Smucker, M. D., & Clarke, C. L. (2012). Modeling user variance in time-biased gain. In Proceedings of the symposium on human\u2013computer interaction and information retrieval (HCIR 2012), Cambridge, CA. doi:10.1145\/2391224.2391227.","DOI":"10.1145\/2391224.2391227"},{"key":"9275_CR23","unstructured":"Song, R., Zhang, M., Sakai, T., Kato, M. P., Liu, Y., Sugimoto, M., Wang, Q., & Orii, N. (2011). Overview of the NTCIR-9 INTENT task. In Proceedings of the 9th NTCIR workshop meeting (pp. 82\u2013105), Tokyo."},{"key":"9275_CR24","doi-asserted-by":"crossref","unstructured":"Sormunen, E. (2002). Liberal relevance criteria of TREC: Counting on negligible documents? In Proceedings of the 25th International ACM SIGIR conference on research and development in information retrieval (SIGIR 2002) (pp. 324\u2013330), Tampere.","DOI":"10.1145\/564376.564433"},{"key":"9275_CR25","doi-asserted-by":"publisher","unstructured":"Turpin, A., Scholer, F., Jarvelin, K., Wu, M., & Culpepper, J. S. (2009). Including summaries in system evaluation. In Proceedings of the 32nd international ACM SIGIR conference on research and development in information retrieval (SIGIR 2009) (pp. 508\u2013515), Boston, MA. doi:10.1145\/1571941.1572029.","DOI":"10.1145\/1571941.1572029"},{"issue":"11","key":"9275_CR26","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1002\/asi.20046","volume":"55","author":"P Vakkari","year":"2004","unstructured":"Vakkari, P., & Sormunen, E. (2004). The influence of relevance levels on the effectiveness of interactive information retrieval. Journal of the American Society for Information Science and Technology, 55(11), 963\u2013969. doi:10.1002\/asi.20046.","journal-title":"Journal of the American Society for Information Science and Technology"},{"issue":"5","key":"9275_CR27","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1016\/S0306-4573(00)00010-8","volume":"36","author":"E Voorhees","year":"2000","unstructured":"Voorhees, E. (2000). Variations in relevance judgments and the measurement of retrieval effectiveness. Information Processing and Management, 36(5), 697\u2013716. doi:10.1016\/S0306-4573(00)00010-8.","journal-title":"Information Processing and Management"},{"key":"9275_CR28","doi-asserted-by":"publisher","unstructured":"Voorhees, E. M. (2001). Evaluation by highly relevant documents. In Proceedings of the 24th international ACM SIGIR conference on research and development in information retrieval (SIGIR 2001) (pp. 74\u201382), New Orleans, LA. doi:10.1145\/383952.383963.","DOI":"10.1145\/383952.383963"},{"key":"9275_CR29","doi-asserted-by":"publisher","unstructured":"Webber, W., Chandar, P., & Carterette, B. (2012). Alternative assessor disagreement and retrieval depth. In Proceedings of the 21st ACM international conference on information and knowledge management (CIKM 2012) (pp. 125\u2013134), New York, NY. doi:10.1145\/2396761.2396781.","DOI":"10.1145\/2396761.2396781"},{"key":"9275_CR30","doi-asserted-by":"publisher","unstructured":"Yilmaz, E., Shokouhi, M., Craswell, N., & Robertson, S. (2010). Expected browsing utility for web search evaluation. In Proceedings of the 19th ACM international conference on information and knowledge management (CIKM 2010) (pp. 1561\u20131564), Toronto, ON. doi:10.1145\/1871437.1871672.","DOI":"10.1145\/1871437.1871672"},{"key":"9275_CR31","doi-asserted-by":"publisher","unstructured":"Zhai, C. X., Cohen, W. W., & Lafferty, J. (2003). Beyond independent relevance: Methods and evaluation metrics for subtopic retrieval. In Proceedings of the 26th International ACM SIGIR conference on research and development in information retrieval (SIGIR 2003) (pp. 10\u201317), Toronto, ON. doi:10.1145\/860435.860440","DOI":"10.1145\/860435.860440"},{"issue":"2","key":"9275_CR32","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1109\/TKDE.2012.252","volume":"26","author":"K Zhou","year":"2014","unstructured":"Zhou, K., Zha, H., Chang, Y., & Xue, G. R. (2014). Learning the gain values and discount factors of discounted cumulative gains. IEEE Transactions on Knowledge and Data Engineering, 26(2), 391\u2013404. doi:10.1109\/TKDE.2012.252.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"}],"container-title":["Information Retrieval Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-015-9275-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-015-9275-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-015-9275-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-015-9275-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:22:56Z","timestamp":1704205376000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-015-9275-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,11,13]]},"references-count":32,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["9275"],"URL":"https:\/\/doi.org\/10.1007\/s10791-015-9275-x","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"value":"1386-4564","type":"print"},{"value":"1573-7659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,11,13]]},"assertion":[{"value":"1 May 2015","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2015","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 November 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}