{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T13:10:01Z","timestamp":1746364201348,"version":"3.40.4"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319113968"},{"type":"electronic","value":"9783319113975"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"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":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-11397-5_11","type":"book-chapter","created":{"date-parts":[[2014,9,2]],"date-time":"2014-09-02T06:41:19Z","timestamp":1409640079000},"page":"147-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Supervised Classification Using Balanced Training"],"prefix":"10.1007","author":[{"given":"Mian","family":"Du","sequence":"first","affiliation":[]},{"given":"Matthew","family":"Pierce","sequence":"additional","affiliation":[]},{"given":"Lidia","family":"Pivovarova","sequence":"additional","affiliation":[]},{"given":"Roman","family":"Yangarber","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2014,9,3]]},"reference":[{"issue":"9","key":"11_CR1","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1016\/j.patcog.2004.03.009","volume":"37","author":"MR Boutell","year":"2004","unstructured":"Boutell, M.R., Luo, J., Shen, X., Brown, C.M.: Learning multi-label scene classification. Pattern Recogn. 37(9), 1757\u20131771 (2004)","journal-title":"Pattern Recogn."},{"issue":"1","key":"11_CR2","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16(1), 321\u2013357 (2002)","journal-title":"J. Artif. Intell. Res."},{"unstructured":"Cisse, M.M., Usunier, N., Arti, T., Gallinari, P.: Robust Bloom filters for large multilabel classification tasks. In: Advances in Neural Information Processing Systems, pp. 1851\u20131859 (2013)","key":"11_CR3"},{"key":"11_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/978-3-642-14640-4_4","volume-title":"New Frontiers in Applied Data Mining","author":"S Dendamrongvit","year":"2010","unstructured":"Dendamrongvit, S., Kubat, M.: Undersampling approach for imbalanced training sets and induction from multi-label text-categorization domains. In: Theeramunkong, T., Nattee, C., Adeodato, P.J.L., Chawla, N., Christen, P., Lenca, P., Poon, J., Williams, G. (eds.) New Frontiers in Applied Data Mining. LNCS, vol. 5669, pp. 40\u201352. Springer, Heidelberg (2010)"},{"key":"11_CR5","first-page":"52","volume":"2","author":"E Dhondt","year":"2012","unstructured":"Dhondt, E., Verberne, S., Weber, N., Koster, C., Boves, L.: Using skipgrams and pos-based feature selection for patent classification. Comput. Linguist. Neth. 2, 52\u201370 (2012)","journal-title":"Comput. Linguist. Neth."},{"issue":"1","key":"11_CR6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s00521-012-1056-5","volume":"22","author":"Z Erenel","year":"2013","unstructured":"Erenel, Z., Alt\u0131n\u00e7ay, H.: Improving the precision-recall trade-off in undersampling-based binary text categorization using unanimity rule. Neural Comput. Appl. 22(1), 83\u2013100 (2013)","journal-title":"Neural Comput. Appl."},{"key":"11_CR7","first-page":"1289","volume":"3","author":"G Forman","year":"2003","unstructured":"Forman, G.: An extensive empirical study of feature selection metrics for text classification. J. Mach. Learn. Res. 3, 1289\u20131305 (2003)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"ACM SIGKDD Explor. Newsl."},{"doi-asserted-by":"crossref","unstructured":"Huang, R., Riloff, E.: Classifying message board posts with an extracted lexicon of patient attributes. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1557\u20131562 (2013)","key":"11_CR9","DOI":"10.18653\/v1\/D13-1162"},{"key":"11_CR10","series-title":"Theory and Applications of Natural Language Processing","first-page":"163","volume-title":"Multi-source, Multilingual Information Extraction and Summarization","author":"S Huttunen","year":"2012","unstructured":"Huttunen, S., Vihavainen, A., Du, M., Yangarber, R.: Predicting relevance of event extraction for the end user. In: Poibeau, T., Saggion, H., Piskorski, J., Yangarber, R. (eds.) Multi-source, Multilingual Information Extraction and Summarization. Theory and Applications of Natural Language Processing, pp. 163\u2013176. Springer, Berlin (2012)"},{"issue":"5","key":"11_CR11","doi-asserted-by":"crossref","first-page":"429","DOI":"10.3233\/IDA-2002-6504","volume":"6","author":"N Japkowicz","year":"2002","unstructured":"Japkowicz, N., Stephen, S.: The class imbalance problem: a systematic study. Intell. Data Anal. 6(5), 429\u2013449 (2002)","journal-title":"Intell. Data Anal."},{"unstructured":"Koller, D., Sahami, M.: Hierarchically classifying documents using very few words. Technical report 1997\u201375, Stanford InfoLab, February 1997","key":"11_CR12"},{"issue":"1","key":"11_CR13","first-page":"25","volume":"30","author":"S Kotsiantis","year":"2006","unstructured":"Kotsiantis, S., Kanellopoulos, D., Pintelas, P., et al.: Handling imbalanced datasets: a review. GESTS Int. Trans. Comput. Sci. Eng. 30(1), 25\u201336 (2006)","journal-title":"GESTS Int. Trans. Comput. Sci. Eng."},{"key":"11_CR14","first-page":"361","volume":"5","author":"DD Lewis","year":"2004","unstructured":"Lewis, D.D., Yang, Y., Rose, T.G., Li, F.: RCV1: a new benchmark collection for text categorization research. J. Mach. Learn. Res. 5, 361\u2013397 (2004)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"11_CR15","doi-asserted-by":"publisher","first-page":"690","DOI":"10.1016\/j.eswa.2007.10.042","volume":"36","author":"Y Liu","year":"2009","unstructured":"Liu, Y., Loh, H.T., Sun, A.: Imbalanced text classification: a term weighting approach. Expert Syst. Appl. 36(1), 690\u2013701 (2009)","journal-title":"Expert Syst. Appl."},{"key":"11_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","first-page":"312","volume-title":"MICAI 2004: Advances in Artificial Intelligence","author":"RC Prati","year":"2004","unstructured":"Prati, R.C., Batista, G.E.A.P.A., Monard, M.C.: Class imbalances versus class overlapping: an analysis of a learning system behavior. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds.) MICAI 2004. LNCS (LNAI), vol. 2972, pp. 312\u2013321. Springer, Heidelberg (2004)"},{"key":"11_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1007\/978-3-642-32695-0_41","volume-title":"PRICAI 2012: Trends in Artificial Intelligence","author":"A Puurula","year":"2012","unstructured":"Puurula, A.: Scalable text classification with sparse generative modeling. In: Anthony, P., Ishizuka, M., Lukose, D. (eds.) PRICAI 2012. LNCS, vol. 7458, pp. 458\u2013469. Springer, Heidelberg (2012)"},{"issue":"2","key":"11_CR18","doi-asserted-by":"publisher","first-page":"790","DOI":"10.1016\/j.ipm.2007.05.012","volume":"44","author":"E Stamatatos","year":"2008","unstructured":"Stamatatos, E.: Author identification: using text sampling to handle the class imbalance problem. Inf. Process. Manage. 44(2), 790\u2013799 (2008)","journal-title":"Inf. Process. Manage."},{"unstructured":"Tikk, D., Bir\u00f3, G.: Experiments with multi-label text classifier on the Reuters collection. In: Proceedings of the International Conference on Computational Cybernetics (ICCC 03), pp. 33\u201338 (2003)","key":"11_CR19"},{"issue":"3","key":"11_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","volume":"3","author":"G Tsoumakas","year":"2007","unstructured":"Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehouse. Min. (IJDWM) 3(3), 1\u201313 (2007)","journal-title":"Int. J. Data Warehouse. Min. (IJDWM)"},{"issue":"1\u20132","key":"11_CR21","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1023\/A:1009982220290","volume":"1","author":"Y Yang","year":"1999","unstructured":"Yang, Y.: An evaluation of statistical approaches to text categorization. Inf. Retrieval 1(1\u20132), 69\u201390 (1999)","journal-title":"Inf. Retrieval"},{"unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: ICML, vol. 97, pp. 412\u2013420 (1997)","key":"11_CR22"},{"issue":"3","key":"11_CR23","doi-asserted-by":"publisher","first-page":"2758","DOI":"10.1016\/j.eswa.2010.08.066","volume":"38","author":"W Zhang","year":"2011","unstructured":"Zhang, W., Yoshida, T., Tang, X.: A comparative study of TF*IDF, LSI and multi-words for text classification. Expert Syst. Appl. 38(3), 2758\u20132765 (2011)","journal-title":"Expert Syst. Appl."},{"unstructured":"Zhuang, D., Zhang, B., Yang, Q., Yan, J., Chen, Z., Chen, Y.: Efficient text classification by weighted proximal SVM. In: Fifth IEEE International Conference on Data Mining (2005)","key":"11_CR24"}],"container-title":["Lecture Notes in Computer Science","Statistical Language and Speech Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-11397-5_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:31:53Z","timestamp":1746361913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-11397-5_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319113968","9783319113975"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-11397-5_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"3 September 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}