{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:43:08Z","timestamp":1760708588076,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2013,5,24]],"date-time":"2013-05-24T00:00:00Z","timestamp":1369353600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2013,5,24]],"date-time":"2013-05-24T00:00:00Z","timestamp":1369353600000},"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"],"published-print":{"date-parts":[[2014,4]]},"DOI":"10.1007\/s10791-013-9225-4","type":"journal-article","created":{"date-parts":[[2013,5,23]],"date-time":"2013-05-23T13:44:11Z","timestamp":1369316651000},"page":"153-176","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["A nonparametric term weighting method for information retrieval based on measuring the divergence from independence"],"prefix":"10.1007","volume":"17","author":[{"given":"\u0130lker","family":"Kocaba\u015f","sequence":"first","affiliation":[]},{"given":"Bekir Taner","family":"Din\u00e7er","sequence":"additional","affiliation":[]},{"given":"Bahar","family":"Karao\u011flan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2013,5,24]]},"reference":[{"key":"9225_CR1","doi-asserted-by":"publisher","DOI":"10.1002\/0471249688","volume-title":"Categorical data analysis","author":"A. Agresti","year":"2002","unstructured":"Agresti, A. (2002). Categorical data analysis. New Jersey: Wiley-Interscience ."},{"issue":"4","key":"9225_CR2","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1145\/582415.582416","volume":"20","author":"G. Amati","year":"2002","unstructured":"Amati, G., van Rijsbergen, C. (2002). Probabilistic models of information retrieval based on measuring the divergence from randomness. ACM Transactions on Information Systems (TOIS), 20(4), 357\u2013389.","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"9225_CR3","volume-title":"Pareto distributions","author":"B. C. Arnold","year":"1983","unstructured":"Arnold, B. C. (1983). Pareto distributions. Fairland, Maryland: International Cooperative Publishing House."},{"key":"9225_CR4","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1002\/asi.4630250505","volume":"25","author":"A. Bookstein","year":"1974","unstructured":"Bookstein, A., Swanson, D. (1974). Probabilistic models for automatic indexing. Journal of the American Society for Information Science (JASIS),25, 312\u2013318.","journal-title":"Journal of the American Society for Information Science (JASIS)"},{"key":"9225_CR5","volume-title":"Distribution free statistical tests","author":"J. V. Bradley","year":"1968","unstructured":"Bradley, J. V. (1968). Distribution free statistical tests. Englewood Cliffs, NJ: Prentice Hall"},{"key":"9225_CR6","doi-asserted-by":"crossref","unstructured":"Church, K. W. (1995). One term or two? In: SIGIR\u201995: Proceedings of the 18th annual international ACM SIGIR conference on research and development in information retrieval (pp 310\u2013318). Seattle, US.","DOI":"10.1145\/215206.215376"},{"key":"9225_CR7","unstructured":"Church, K. W., Gale, W. (1995). Inverse document frequency (IDF): A measure of deviations from Poisson. In: D. Yarowsky, & K. Church (Eds.), Proceedings of the ACL 3rd workshop on very large corpora, ACL, MIT (pp 121\u2013130)."},{"key":"9225_CR8","unstructured":"Clarke, C. L. A., Craswell, N., Soboroff, I., & Cormack, G. V. (2010). Overview of the trec 2010 web track. In: Proceedings of the 19th text retrieval conference (TREC\u201910), Gaithersburg, MD, USA."},{"key":"9225_CR9","doi-asserted-by":"crossref","unstructured":"Clinchant, A., Gaussier, E. (2010). Information-based models for ad hoc ir. In: Proceeding of the 33rd annual international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201910), (pp 234\u2013241).","DOI":"10.1145\/1835449.1835490"},{"key":"9225_CR10","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1145\/322047.322053","volume":"25","author":"W. Cooper","year":"1978","unstructured":"Cooper, W., & Maron, M. (1978). Foundations of probabilistic and utility-theoretic indexing. Journal of Association for Computing Machinery,25, 67\u201380.","journal-title":"Journal of Association for Computing Machinery"},{"key":"9225_CR11","unstructured":"Cormack, G. V., Smucker, M. D., & Clarke, C. L. A. (2010). Efficient and effective spam filtering and re-ranking for large web datasets URL http:\/\/arxiv.org\/abs\/1004.5168, retrieved from http:\/\/arxiv.org\/abs\/1004.5168v1, 1004.5168."},{"issue":"4","key":"9225_CR12","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1108\/eb026683","volume":"35","author":"W. B. Croft","year":"1979","unstructured":"Croft, W. B., & Harper, D. J. (1979). Using probabilistic models of document retrieval without relevance information. Journal of Documentation, 35(4), 285\u2013295.","journal-title":"Journal of Documentation"},{"key":"9225_CR13","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1002\/asi.5090160403","volume":"16","author":"F. Damerau","year":"1965","unstructured":"Damerau, F. (1965). An experiment in automatic indexing. American Documentation,16, 283\u2013289.","journal-title":"American Documentation"},{"key":"9225_CR14","unstructured":"Din\u00e7er, B. T. (2012). Irra at trec 2012: Index term weighting based on divergence from independence model. In: Proceedings of the 21th text retrieval conference (TREC\u201912), Gaithersburg, MD."},{"key":"9225_CR15","unstructured":"Din\u00e7er, B. T., Kocaba\u015f, I., & Karao\u011flan, B. (2009). Irra at trec 2009: Index term weighting based on divergence from independence model. In: Proceedings of the 18th text retrieval conference (TREC\u201909), Gaithersburg, MD."},{"key":"9225_CR16","unstructured":"Din\u00e7er, B. T., Kocaba\u015f, I., & Karao\u011flan, B. (2010). Irra at trec 2010: Index term weighting based on divergence from independence model. In: Proceedings of the 19th text retrieval conference (TREC\u201910), Gaithersburg, MD."},{"issue":"1","key":"9225_CR17","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/0306-4573(89)90091-5","volume":"25","author":"N. Fuhr","year":"1989","unstructured":"Fuhr, N. (1989). Models for retrieval with probabilistic indexing. Journal of Information Processing and Management, 25(1), 55\u201372.","journal-title":"Journal of Information Processing and Management"},{"key":"9225_CR18","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1002\/asi.4630260402","volume":"26","author":"S. Harter","year":"1975","unstructured":"Harter, S. (1975). A probabilistic approach to automatic keyword indexing. Part I: On the distribution of specialty words in a technical literature. Journal of the American Society for Information Science (JASIS), 26, 197\u2013216.","journal-title":"Journal of the American Society for Information Science (JASIS)"},{"key":"9225_CR19","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1002\/asi.4630260504","volume":"26","author":"S. Harter","year":"1975","unstructured":"Harter, S. (1975). A probabilistic approach to automatic keyword indexing. Part II: An algorithm for probabilistic indexing. Journal of the American Society for Information Science (JASIS), 26, 280\u2013289.","journal-title":"Journal of the American Society for Information Science (JASIS)"},{"key":"9225_CR20","doi-asserted-by":"crossref","unstructured":"He, B., & Ounis, I. (2003). A study of parameter tuning for term frequency normalization. In: Proceedings of the 12th international conference on information and knowledge management, New Orleans, LA.","DOI":"10.1145\/956863.956867"},{"key":"9225_CR21","doi-asserted-by":"crossref","unstructured":"He, B., & Ounis, I. (2005). Term frequency normalisation tuning for BM25 and DFR model. In: Proceedings of the 27th European conference on information retrieval (ECIR\u201905) (pp. 200\u2013214).","DOI":"10.1007\/978-3-540-31865-1_15"},{"issue":"2","key":"9225_CR22","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s007999900025","volume":"3","author":"D. Hiemstra","year":"2000","unstructured":"Hiemstra, D. (2000). A probabilistic justification for using tf.idf term weighting in information retrieval. International Journal on Digital Libraries, 3(2), 131\u2013139.","journal-title":"International Journal on Digital Libraries"},{"key":"9225_CR23","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-94-010-3296-4_1","volume-title":"Information and inference","author":"J. Hintikka","year":"1970","unstructured":"Hintikka, J. (1970). On semantic information. In: J. Hintikka, & P. Suppes (Eds.), Information and inference (pp. 3\u201327). Dordrecht: Synthese Library."},{"key":"9225_CR24","unstructured":"Hoaglin, D. C., Mosteller, F., & Tukey, J. W. (Eds.) (1983). Understanding robust and exploratory data analysis. Wiley series in probability and mathematical statistics. Wiley-Interscience"},{"key":"9225_CR25","volume-title":"Nonparametric statistical methods","author":"M. Hollander","year":"1999","unstructured":"Hollander, M., & Wolfe, D. A. (1999). Nonparametric statistical methods. Hoboken, NJ: Wiley"},{"key":"9225_CR26","doi-asserted-by":"crossref","unstructured":"Hull, D. (1993). Using statistical testing in the evaluation of retrieval experiments. In: Proceedings of the 16th annual international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201993), (pp 329\u2013338).","DOI":"10.1145\/160688.160758"},{"issue":"2","key":"9225_CR27","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1147\/rd.22.0159","volume":"2","author":"H. P. Luhn","year":"1958","unstructured":"Luhn, H. P. (1958). The automatic creation of literature abstracts. IBM Journal of Research and Development 2(2):159\u2013165, doi: http:\/\/dx.doi.org\/10.1147\/rd.22.0159","journal-title":"IBM Journal of Research and Development"},{"key":"9225_CR28","unstructured":"Macdonald, C., He, B., Plachouras, V., & Ounis, I. (2005). University of Glasgow at TREC 2005: Experiments in terabyte and enterprise tracks with terrier. In: Proceedings of TREC 2005."},{"key":"9225_CR29","doi-asserted-by":"crossref","unstructured":"Margulis, E. (1992). N-poisson document modelling. In: Proceedings of the 15th International ACM SIGIR conference on research and development in information retrieval (ACM\u2013SIGIR\u201992) (pp 177\u2013189).","DOI":"10.1145\/133160.133195"},{"issue":"3","key":"9225_CR30","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1145\/321033.321035","volume":"7","author":"M. E. Maron","year":"1960","unstructured":"Maron, M. E., & Kuhns, J. L. (1960). On relevance, probabilistic indexing, and information retrieval. Journal of the Association for Computing Machinery, 7(3), 216\u2013244.","journal-title":"Journal of the Association for Computing Machinery"},{"key":"9225_CR31","volume-title":"Data analysis and regression","author":"F. Mosteller","year":"1977","unstructured":"Mosteller, F., & Tukey, J. (1977). Data analysis and regression. Reading, MA: Addison-Wesley."},{"key":"9225_CR32","unstructured":"Ounis, I., Lioma, C., Macdonald, C., & Plachouras, V. (2007). Research directions in Terrier. Novatica\/UPGRADE special issue on web information Access, Ricardo Baeza-Yates et\u00a0al (Eds.), Invited paper."},{"key":"9225_CR33","doi-asserted-by":"crossref","unstructured":"Ponte, J., & Croft, B. (1998). A language modeling approach in information retrieval. In: Proceedings of the 21st annual international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201998). (pp 275\u2013281).","DOI":"10.1145\/290941.291008"},{"key":"9225_CR34","volume-title":"The logic of scientific discovery","author":"K. Popper","year":"1995","unstructured":"Popper, K. (1995). The logic of scientific discovery. London: Routledge."},{"issue":"5","key":"9225_CR35","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1108\/00220410410560582","volume":"60","author":"S. Robertson","year":"2004","unstructured":"Robertson, S. (2004). Understanding inverse document frequency: On theoretical arguments for idf. Journal of Documentation, 60(5), 503\u2013520.","journal-title":"Journal of Documentation"},{"key":"9225_CR36","doi-asserted-by":"crossref","unstructured":"Robertson, S., & Walker, S. (1994). Some simple approximations to the 2-Poisson model for probabilistic weighted retrieval. In: Proceedings of the 17th annual international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201994) (pp 232\u2013241).","DOI":"10.1007\/978-1-4471-2099-5_24"},{"key":"9225_CR37","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1002\/asi.4630270302","volume":"27","author":"S. E. Robertson","year":"1988","unstructured":"Robertson, S. E., & Jones, K. S. (1976). Relevance weighting of search terms. Journal of the American Society for Information Science (JASIS),27, 129\u2013146.","journal-title":"Journal of the American Society for Information Science (JASIS)"},{"key":"9225_CR38","first-page":"35","volume-title":"Information retrieval research, chap 4","author":"S. E. Robertson","year":"1981","unstructured":"Robertson, S. E., van Rijsbergen, C. J., & Porter, M. (1981). Probabilistic models of indexing and searching. In: S. E. Robertson, C. J. van Rijsbergen, & P. Williams (Eds.), Information retrieval research, chap 4 (pp. 35\u201356). Oxford: Butterworths."},{"key":"9225_CR39","unstructured":"Robertson, S. E., Walker, S., & Beaulieu, M. (1999). Okapi at TREC-7: Automatic ad hoc, filtering, VLC and interactive track. In: The seventh text REtrieval conference (TREC-7), NIST Special Publication 500:242 (pp 253\u2013264)."},{"issue":"5","key":"9225_CR40","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G. Salton","year":"1988","unstructured":"Salton, G., & Buckley, C. (1988). Term-weighting approaches in automatic text retrieval. Information Processing and Management, 24(5), 513\u2013523.","journal-title":"Information Processing and Management"},{"key":"9225_CR41","first-page":"3","volume-title":"The mathematical theory of communication","author":"C. E. Shannon","year":"1949","unstructured":"Shannon, C. E. (1949). The mathematical theory of communication. In: C. E. Shannon, & W. Weaver (Eds.), The mathematical theory of communication (pp. 3\u201391). Urbana: The University of Illinois Press."},{"key":"9225_CR42","doi-asserted-by":"crossref","unstructured":"Singhal, A., Buckley, C., Mitra, M., & Mitra, A. (1996). Pivoted document length normalization. In: Proceedings of the 19th international ACM SIGIR conference on research and development in information retrieval (SIGIR\u201996), (pp 21\u201329).","DOI":"10.1145\/243199.243206"},{"issue":"1","key":"9225_CR43","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1108\/eb026526","volume":"28","author":"K. Sparck Jones","year":"1972","unstructured":"Sparck Jones, K. (1972). A statistical interpretation of term specificity and its application in retrieval. Journal of Documentation, 28(1), 11\u201321.","journal-title":"Journal of Documentation"},{"key":"9225_CR44","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1214\/aoms\/1177731566","volume":"13","author":"J. Wolfowitz","year":"1942","unstructured":"Wolfowitz, J. (1942). Additive partition functions and a class of statistical hypotheses. Annuals of Statistics, 13, 247\u2013279.","journal-title":"Annuals of Statistics"},{"key":"9225_CR45","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1145\/195705.195713","volume":"16","author":"S. Wong","year":"1995","unstructured":"Wong, S., & Yao, Y. (1995). On modeling information retrieval with probabilistic inference. ACM Transactions on Information Systems, 16, 38\u201368.","journal-title":"ACM Transactions on Information Systems"},{"issue":"2","key":"9225_CR46","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1145\/984321.984322","volume":"22","author":"C. Zhai","year":"2004","unstructured":"Zhai, C., Lafferty, J. (2004). A study of smoothing methods for language models applied to information retrieval. ACM Transactions on Information Systems (TOIS), 22(2), 179\u2013214.","journal-title":"ACM Transactions on Information Systems (TOIS)"}],"container-title":["Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-013-9225-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-013-9225-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-013-9225-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-013-9225-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,2]],"date-time":"2024-01-02T14:09:08Z","timestamp":1704204548000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-013-9225-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,5,24]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2014,4]]}},"alternative-id":["9225"],"URL":"https:\/\/doi.org\/10.1007\/s10791-013-9225-4","relation":{},"ISSN":["1386-4564","1573-7659"],"issn-type":[{"type":"print","value":"1386-4564"},{"type":"electronic","value":"1573-7659"}],"subject":[],"published":{"date-parts":[[2013,5,24]]},"assertion":[{"value":"6 September 2012","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 May 2013","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 May 2013","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"}]}}