{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T20:11:41Z","timestamp":1771272701069,"version":"3.50.1"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T00:00:00Z","timestamp":1590364800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Adv Data Anal Classif"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s11634-020-00399-3","type":"journal-article","created":{"date-parts":[[2020,5,25]],"date-time":"2020-05-25T04:02:25Z","timestamp":1590379345000},"page":"759-770","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Mixtures of Dirichlet-Multinomial distributions for supervised and unsupervised classification of short text data"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1161-6145","authenticated-orcid":false,"given":"Laura","family":"Anderlucci","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3278-5266","authenticated-orcid":false,"given":"Cinzia","family":"Viroli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,25]]},"reference":[{"key":"399_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-642-59789-3_26","volume-title":"Data analysis, classification, and related methods","author":"C Ambroise","year":"2000","unstructured":"Ambroise C, Govaert G (2000) Em algorithm for partially known labels. In: Kiers HAL, Rasson J-P, Groenen PJF, Schader M (eds) Data analysis, classification, and related methods. Springer, Berlin, pp 161\u2013166"},{"issue":"1","key":"399_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"key":"399_CR3","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman J, Olshen R, Stone C (1984) Classification and regression trees. Wadsworth, Belmont"},{"issue":"3","key":"399_CR4","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273\u2013297","journal-title":"Mach Learn"},{"key":"399_CR5","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21\u201327","journal-title":"IEEE Trans Inf Theory"},{"key":"399_CR6","unstructured":"Feinerer I, Hornik K (2018) tm: text Mining Package. R package version 0.7-6"},{"issue":"5","key":"399_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v025.i05","volume":"25","author":"I Feinerer","year":"2008","unstructured":"Feinerer I, Hornik K, Meyer D (2008) Text mining infrastructure in R. J Stat Softw 25(5):1\u201354","journal-title":"J Stat Softw"},{"key":"399_CR8","first-page":"385","volume":"69","author":"D Hand","year":"2001","unstructured":"Hand D, Yu K (2001) Idiot\u2019s Bayes\u2014not so stupid after all? Int Stat Rev 69:385\u2013398","journal-title":"Int Stat Rev"},{"issue":"2\u20133","key":"399_CR9","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1080\/00437956.1954.11659520","volume":"10","author":"ZS Harris","year":"1954","unstructured":"Harris ZS (1954) Distributional structure. Word 10(2\u20133):146\u2013162","journal-title":"Word"},{"issue":"2","key":"399_CR10","doi-asserted-by":"publisher","first-page":"e30126","DOI":"10.1371\/journal.pone.0030126","volume":"7","author":"I Holmes","year":"2012","unstructured":"Holmes I, Harris K, Quince C (2012) Dirichlet multinomial mixtures: generative models for microbial metagenomics. PLoS ONE 7(2):e30126","journal-title":"PLoS ONE"},{"key":"399_CR11","unstructured":"John G, Langley P (1995) Estimating continuous distributions in Bayesian classifiers. In: Proceedings of the 11th conference on uncertainty in artificial intelligence, pp. 338\u2013345"},{"key":"399_CR12","first-page":"4","volume":"1","author":"A Khan","year":"2010","unstructured":"Khan A, Baharudin B, Lee LH, Khan K, Tronoh UTP (2010) A review of machine learning algorithms for text-documents classification. J Adv Inf Technol 1:4\u201320","journal-title":"J Adv Inf Technol"},{"key":"399_CR13","doi-asserted-by":"crossref","unstructured":"Ko Y (2012) A study of term weighting schemes using class information for text classification. In: SIGIR\u201912\u2014proceedings of the international ACM SIGIR conference on research and development in information retrieval","DOI":"10.1145\/2348283.2348453"},{"key":"399_CR14","unstructured":"Kohavi R et\u00a0al (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence, vol\u00a02. Montreal, Canada, pp 1137\u20131145"},{"issue":"5","key":"399_CR15","first-page":"9","volume":"5","author":"P Kumbhar","year":"2016","unstructured":"Kumbhar P, Mali M (2016) A survey on feature selection techniques and classification algorithms for efficient text classification. Int J Sci Res 5(5):9","journal-title":"Int J Sci Res"},{"key":"399_CR16","doi-asserted-by":"crossref","unstructured":"Lai S, Xu L, Liu K, Zhao J (2015) Recurrent convolutional neural networks for text classification. In: Proceedings of the twenty-ninth AAAI conference on artificial intelligence, AAAI\u201915. AAAI Press, pp 2267\u20132273","DOI":"10.1609\/aaai.v29i1.9513"},{"key":"399_CR17","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1023\/A:1007692713085","volume":"39","author":"K Nigam","year":"2000","unstructured":"Nigam K, McCallum A, Thrun S, Mitchell T (2000) Text classification from labeled and unlabeled documents using EM. Mach Learn 39:103\u2013134","journal-title":"Mach Learn"},{"issue":"5","key":"399_CR18","doi-asserted-by":"publisher","first-page":"1260","DOI":"10.1016\/j.ipm.2006.11.001","volume":"43","author":"L Rigouste","year":"2007","unstructured":"Rigouste L, Capp\u00e9 O, Yvon F (2007) Inference and evaluation of the multinomial mixture model for text clustering. Inf Process Manag 43(5):1260\u20131280","journal-title":"Inf Process Manag"},{"issue":"1","key":"399_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebastiani","year":"2002","unstructured":"Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv 34(1):1\u201347","journal-title":"ACM Comput Surv"},{"key":"399_CR20","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1214\/ss\/1056397488","volume":"18","author":"R Tibshirani","year":"2003","unstructured":"Tibshirani R, Hastie T, Narasimhan B, Chu G (2003) Class prediction by nearest shrunken centroids, with applications to DNA microarrays. Stat Sci 18:104\u2013117","journal-title":"Stat Sci"},{"key":"399_CR21","doi-asserted-by":"crossref","unstructured":"Yin J, Wang J (2014) A Dirichlet multinomial mixture model-based approach for short text clustering. In: Proceedings of the 20th ACM SIGKDD international conference on KDDM, KDD \u201914, New York. ACM, pp 233\u2013242","DOI":"10.1145\/2623330.2623715"},{"key":"399_CR22","doi-asserted-by":"publisher","DOI":"10.2200\/S00196ED1V01Y200906AIM006","volume-title":"Introduction to semi-supervised learning","author":"X Zhu","year":"2009","unstructured":"Zhu X, Goldberg AB (2009) Introduction to semi-supervised learning. Morgan & Claypool Publishers, San Rafael"}],"container-title":["Advances in Data Analysis and Classification"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-020-00399-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11634-020-00399-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11634-020-00399-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,24]],"date-time":"2022-10-24T19:29:49Z","timestamp":1666639789000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11634-020-00399-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,25]]},"references-count":22,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["399"],"URL":"https:\/\/doi.org\/10.1007\/s11634-020-00399-3","relation":{},"ISSN":["1862-5347","1862-5355"],"issn-type":[{"value":"1862-5347","type":"print"},{"value":"1862-5355","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,25]]},"assertion":[{"value":"12 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}