{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:43:44Z","timestamp":1750308224154,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":11,"publisher":"ACM","license":[{"start":{"date-parts":[[2004,8,22]],"date-time":"2004-08-22T00:00:00Z","timestamp":1093132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2004,8,22]]},"DOI":"10.1145\/1014052.1016922","type":"proceedings-article","created":{"date-parts":[[2004,10,7]],"date-time":"2004-10-07T17:39:48Z","timestamp":1097170788000},"page":"829-834","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":16,"title":["Document preprocessing for naive Bayes classification and clustering with mixture of multinomials"],"prefix":"10.1145","author":[{"given":"Dmitry","family":"Pavlov","sequence":"first","affiliation":[{"name":"Yahoo Inc., Sunnyvale, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ramnath","family":"Balasubramanyan","sequence":"additional","affiliation":[{"name":"Yahoo Inc., Sunnyvale, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byron","family":"Dom","sequence":"additional","affiliation":[{"name":"Yahoo Inc., Sunnyvale, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shyam","family":"Kapur","sequence":"additional","affiliation":[{"name":"Yahoo Inc., Sunnyvale, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jignashu","family":"Parikh","sequence":"additional","affiliation":[{"name":"Yahoo Inc., Sunnyvale, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2004,8,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"IJCAI Workshop on machine learning for information filtering.","author":"Berger A.","year":"1999","unstructured":"A. Berger . Error-correcting output coding for text classification . In IJCAI Workshop on machine learning for information filtering. 1999 . A. Berger. Error-correcting output coding for text classification. In IJCAI Workshop on machine learning for information filtering. 1999."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007413511361"},{"key":"e_1_3_2_1_3_1","volume-title":"Pattern Classification and Scene Analysis John Wiley and Sons","author":"Duda R.O.","year":"1973","unstructured":"R.O. Duda and P.E. Hart . Pattern Classification and Scene Analysis John Wiley and Sons , 1973 . R.O. Duda and P.E. Hart. Pattern Classification and Scene Analysis John Wiley and Sons, 1973."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176347279"},{"key":"e_1_3_2_1_5_1","volume-title":"AAAI-98 Workshop on Learning for Text Categorization","author":"McCallum A.","year":"1998","unstructured":"A. McCallum and K. Nigam . A comparison of event models for naive bayes text classification . In AAAI-98 Workshop on Learning for Text Categorization 1998 . A. McCallum and K. Nigam. A comparison of event models for naive bayes text classification. In AAAI-98 Workshop on Learning for Text Categorization 1998."},{"key":"e_1_3_2_1_6_1","volume-title":"Mixture Models Marcel Dekker","author":"McLachlan G.","year":"1988","unstructured":"G. McLachlan and K. Basford . Mixture Models Marcel Dekker , New York , 1988 . G. McLachlan and K. Basford. Mixture Models Marcel Dekker, New York, 1988."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2000.906052"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/347090.347155"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems","author":"Platt J.","year":"1999","unstructured":"J. Platt . Using sparseness and analytic QP to speed training of support vector machines . In Advances in Neural Information Processing Systems , 1999 . J. Platt. Using sparseness and analytic QP to speed training of support vector machines. In Advances in Neural Information Processing Systems, 1999."},{"key":"e_1_3_2_1_10_1","volume-title":"ICML","author":"Rennie J.","year":"2003","unstructured":"J. Rennie , L. Shih , J. Teevan , and D. Karger . Tackling the poor assumptions of naive bayes text classifiers . In ICML , 2003 . J. Rennie, L. Shih, J. Teevan, and D. Karger. Tackling the poor assumptions of naive bayes text classifiers. In ICML, 2003."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39857-8_40"}],"event":{"name":"KDD04: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"],"location":"Seattle WA USA","acronym":"KDD04"},"container-title":["Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1016922","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1014052.1016922","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:31:25Z","timestamp":1750264285000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1014052.1016922"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2004,8,22]]},"references-count":11,"alternative-id":["10.1145\/1014052.1016922","10.1145\/1014052"],"URL":"https:\/\/doi.org\/10.1145\/1014052.1016922","relation":{},"subject":[],"published":{"date-parts":[[2004,8,22]]},"assertion":[{"value":"2004-08-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}