{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T11:41:57Z","timestamp":1725536517131},"publisher-location":"Berlin, Heidelberg","reference-count":30,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642033476"},{"type":"electronic","value":"9783642033483"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-03348-3_33","type":"book-chapter","created":{"date-parts":[[2009,8,8]],"date-time":"2009-08-08T01:01:20Z","timestamp":1249693280000},"page":"338-349","source":"Crossref","is-referenced-by-count":1,"title":["A Hybrid Statistical Data Pre-processing Approach for Language-Independent Text Classification"],"prefix":"10.1007","author":[{"given":"Yanbo J.","family":"Wang","sequence":"first","affiliation":[]},{"given":"Frans","family":"Coenen","sequence":"additional","affiliation":[]},{"given":"Robert","family":"Sanderson","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"33_CR1","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1145\/170035.170072","volume-title":"Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, Washington, DC, USA","author":"R. Agrawal","year":"1993","unstructured":"Agrawal, R., Imielinski, T., Swami, A.: Mining Association Rules between Sets of Items in Large Database. In: Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, Washington, DC, USA, May 1993, pp. 207\u2013216. ACM Press, New York (1993)"},{"key":"33_CR2","first-page":"115","volume-title":"Proceedings of the Third International Conference on Knowledge Discovery and Data Mining, Newport Beach, CA, USA","author":"K. Ali","year":"1997","unstructured":"Ali, K., Manganaris, S., Srikant, R.: Partial Classification using Association Rules. In: Proceedings of the Third International Conference on Knowledge Discovery and Data Mining, Newport Beach, CA, USA, August 1997, pp. 115\u2013118. AAAI Press, Menlo Park (1997)"},{"key":"33_CR3","first-page":"19","volume-title":"Proceedings of the 2002 IEEE International Conference on Data Mining, Maebashi City, Japan","author":"M.-L. Antonie","year":"2002","unstructured":"Antonie, M.-L., Za\u00efane, O.R.: Text Document Categorization by Term Association. In: Proceedings of the 2002 IEEE International Conference on Data Mining, Maebashi City, Japan, December 2002, pp. 19\u201326. IEEE Computer Society, Los Alamitos (2002)"},{"key":"33_CR4","doi-asserted-by":"crossref","unstructured":"Church, K.W., Hanks, P.: Word Association Norms, Mutual Information, and Lexicography. In: Proceedings of the 27th Annual Meeting on Association for Computational Linguistics, Vancouver, BC, Canada, pp. 76\u201383. Association for Computational Linguistics (1989)","DOI":"10.3115\/981623.981633"},{"key":"33_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/11430919_27","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"F. Coenen","year":"2005","unstructured":"Coenen, F., Leng, P., Zhang, L.: Threshold Tuning for Improved Classification Association Rule Mining. In: Ho, T.-B., Cheung, D., Liu, H. (eds.) PAKDD 2005. LNCS, vol.\u00a03518, pp. 216\u2013225. Springer, Heidelberg (2005)"},{"key":"33_CR6","first-page":"838","volume-title":"Proceedings of the 5th International Conference on Machine Learning and Data Mining","author":"F. Coenen","year":"2007","unstructured":"Coenen, F., Leng, P., Sanderson, R., Wang, Y.J.: Statistical Identification of Key Phrases for Text Classification. In: Proceedings of the 5th International Conference on Machine Learning and Data Mining, Leipzig, Germany, July 2007, pp. 838\u2013853. Springer, Heidelberg (2007)"},{"key":"33_CR7","first-page":"115","volume-title":"Proceedings of the 12th International Conference on Machine Learning","author":"W.W. Cohen","year":"1995","unstructured":"Cohen, W.W.: Fast Effective Rule Induction. In: Proceedings of the 12th International Conference on Machine Learning, Tahoe City, CA, USA, July 1995, pp. 115\u2013123. Morgan Kaufmann, San Francisco (1995)"},{"key":"33_CR8","first-page":"223","volume-title":"Proceedings of the Third International Conference on Web Information Systems Engineering Workshop","author":"Z.-H. Deng","year":"2002","unstructured":"Deng, Z.-H., Tang, S.-W., Yang, D.-Q., Zhang, M., Wu, X.-B., Yang, M.: Two Odds-radio-based Text Classification Algorithms. In: Proceedings of the Third International Conference on Web Information Systems Engineering Workshop, Singapore, December 2002, pp. 223\u2013231. IEEE Computer Society, Los Alamitos (2002)"},{"key":"33_CR9","volume-title":"Transmission of Information \u2013 A Statistical Theory of Communication","author":"R.M. Fano","year":"1961","unstructured":"Fano, R.M.: Transmission of Information \u2013 A Statistical Theory of Communication. The MIT Press, Cambridge (1961)"},{"issue":"1","key":"33_CR10","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1007\/s10115-004-0177-2","volume":"8","author":"D. Fragoudis","year":"2005","unstructured":"Fragoudis, D., Meretaskis, D., Likothanassis, S.: Best Terms: An Efficient Feature-Selection Algorithm for Text Categorization. Knowledge and Information Systems\u00a08(1), 16\u201333 (2005)","journal-title":"Knowledge and Information Systems"},{"issue":"1","key":"33_CR11","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.: Models for Retrieval with Probabilistic Indexing. Information Processing and Management\u00a025(1), 55\u201372 (1989)","journal-title":"Information Processing and Management"},{"issue":"3","key":"33_CR12","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1145\/125187.125189","volume":"9","author":"N. Fuhr","year":"1991","unstructured":"Fuhr, N., Buckley, C.: A Probabilistic Learning Approach for Document Indexing. ACM Transactions on Information System\u00a09(3), 223\u2013248 (1991)","journal-title":"ACM Transactions on Information System"},{"key":"33_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/3-540-45268-0_6","volume-title":"Research and Advanced Technology for Digital Libraries","author":"L. Galavotti","year":"2000","unstructured":"Galavotti, L., Sebastiani, F., Simi, M.: Experiments on the Use of Feature Selection and Negative Evidence in Automated Text Categorization. In: Borbinha, J.L., Baker, T. (eds.) ECDL 2000. LNCS, vol.\u00a01923, pp. 59\u201368. Springer, Heidelberg (2000)"},{"key":"33_CR14","first-page":"103","volume-title":"Survey of Text Mining \u2013 Clustering, Classification, and Retrieval","author":"M. Kobayashi","year":"2004","unstructured":"Kobayashi, M., Aono, M.: Vector Space Models for Search and Cluster Mining. In: Berry, M.W. (ed.) Survey of Text Mining \u2013 Clustering, Classification, and Retrieval, pp. 103\u2013122. Springer, New York (2004)"},{"key":"33_CR15","first-page":"369","volume-title":"Proceedings of the 2001 IEEE International Conference on Data Mining","author":"W. Li","year":"2001","unstructured":"Li, W., Han, J., Pei, J.: CMAR: Accurate and Efficient Classification based on Multiple Class-association Rules. In: Proceedings of the 2001 IEEE International Conference on Data Mining, San Jose, CA, USA, November-December 2001, pp. 369\u2013376. IEEE Computer Society Press, Los Alamitos (2001)"},{"key":"33_CR16","first-page":"80","volume-title":"Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining","author":"B. Liu","year":"1998","unstructured":"Liu, B., Hsu, W., Ma, Y.: Integrating Classification and Association Rule Mining. In: Proceedings of the Fourth International Conference on Knowledge Discovery and Data Mining, August 1998, pp. 80\u201386. AAAI Press, Menlo Park (1998)"},{"issue":"4","key":"33_CR17","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1109\/5254.784084","volume":"14","author":"D. Mladenic","year":"1999","unstructured":"Mladenic, D.: Text-learning and Related Intelligent Agents: A survey. IEEE Intelligent Systems\u00a014(4), 44\u201354 (1999)","journal-title":"IEEE Intelligent Systems"},{"key":"33_CR18","first-page":"67","volume-title":"Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"H.T. Ng","year":"1997","unstructured":"Ng, H.T., Goh, W.B., Low, K.L.: Feature Selection, Perceptron Learning, and a Usability Case Study for Text Categorization. In: Proceedings of the 20th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, Philadelphia, PA, USA, July 1997, pp. 67\u201373. ACM Press, New York (1997)"},{"key":"33_CR19","volume-title":"C4.5: Programs for Machine Learning","author":"J.R. Quinlan","year":"1993","unstructured":"Quinlan, J.R.: C4.5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Francisco (1993)"},{"issue":"11","key":"33_CR20","first-page":"613","volume":"18","author":"G. Salton","year":"1975","unstructured":"Salton, G., Wong, A., Yang, C.S.: A Vector Space Model for Automatic Indexing. Information Retrieval and Language Processing\u00a018(11), 613\u2013620 (1975)","journal-title":"Information Retrieval and Language Processing"},{"issue":"5","key":"33_CR21","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.: Term-weighting Approaches in Automatic Text Retrieval. Information Processing & Management\u00a024(5), 513\u2013523 (1988)","journal-title":"Information Processing & Management"},{"key":"33_CR22","unstructured":"Scheffer, T., Wrobel, S.: Text Classification beyond the Bag-of-words Representation. In: Proceedings of the Workshop on Text Learning, held at the Nineteenth International Conference on Machine Learning, Sydney, Australia (2002)"},{"issue":"1","key":"33_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F. Sebastiani","year":"2002","unstructured":"Sebastiani, F.: Machine Learning in Automated Text Categorization. ACM Computing Surveys\u00a034(1), 1\u201347 (2002)","journal-title":"ACM Computing Surveys"},{"key":"33_CR24","first-page":"490","volume-title":"Proceedings of the 5th International Conference on Machine Learning and Data Mining","author":"Y. Shidara","year":"2007","unstructured":"Shidara, Y., Nakamura, A., Kudo, M.: CCIC: Consistent Common Itemsets Classifier. In: Proceedings of the 5th International Conference on Machine Learning and Data Mining, Leipzig, Germany, July 2007, pp. 490\u2013498. Springer, Heidelberg (2007)"},{"key":"33_CR25","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/978-3-540-85836-2_34","volume-title":"Proceedings of the 10th International Conference on Data Warehousing and Knowledge Discovery","author":"Y.J. Wang","year":"2008","unstructured":"Wang, Y.J., Sanderson, R., Coenen, F., Leng, P.H.: Document-Base Extraction for Single-Label Text Classification. In: Proceedings of the 10th International Conference on Data Warehousing and Knowledge Discovery, Turin, Italy, September 2008, pp. 357\u2013367. Springer, Heidelberg (2008)"},{"key":"33_CR26","unstructured":"Wiener, E., Pedersen, J.O., Weigend, A.S.: A Neural Network Approach to Topic Spotting. In: Proceedings of the 4th Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, USA, April 1995, pp. 317\u2013332 (1995)"},{"key":"33_CR27","first-page":"412","volume-title":"Proceedings of the Fourteenth International Conference on Machine Learning","author":"Y. Yang","year":"1997","unstructured":"Yang, Y., Pedersen, J.O.: A Comparative Study on Feature Selection in Text Categorization. In: Proceedings of the Fourteenth International Conference on Machine Learning, Nashville, TN, USA, July 1997, pp. 412\u2013420. Morgan Kaufmann Publishers, San Francisco (1997)"},{"key":"33_CR28","first-page":"331","volume-title":"Proceedings of the Third SIAM International Conference on Data Mining","author":"X. Yin","year":"2003","unstructured":"Yin, X., Han, J.: CPAR: Classification based on Predictive Association Rules. In: Proceedings of the Third SIAM International Conference on Data Mining, San Francisco, CA, USA, May 2003, pp. 331\u2013335. SIAM, Philadelphia (2003)"},{"key":"33_CR29","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/11562382_36","volume-title":"Information Retrieval Technology","author":"Y. Yoon","year":"2005","unstructured":"Yoon, Y., Lee, G.G.: Practical Application of Associative Classifier for Document Classification. In: Lee, G.G., Yamada, A., Meng, H., Myaeng, S.-H. (eds.) AIRS 2005. LNCS, vol.\u00a03689, pp. 467\u2013478. Springer, Heidelberg (2005)"},{"key":"33_CR30","unstructured":"Zheng, Z., Srihari, R.: Optimally Combining Positive and Negative Features for Text Categorization. In: Proceedings of the 2003 ICML Workshop on Learning from Imbalanced Data Sets II, Washington, DC, USA (2003)"}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03348-3_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,1,25]],"date-time":"2019-01-25T08:33:28Z","timestamp":1548405208000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03348-3_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642033476","9783642033483"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03348-3_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}