{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T16:02:02Z","timestamp":1772294522390,"version":"3.50.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2005,9,9]],"date-time":"2005-09-09T00:00:00Z","timestamp":1126224000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2006,4]]},"DOI":"10.1007\/s10115-005-0209-6","type":"journal-article","created":{"date-parts":[[2005,9,9]],"date-time":"2005-09-09T02:25:37Z","timestamp":1126232737000},"page":"468-491","source":"Crossref","is-referenced-by-count":15,"title":["Higher order feature selection for text classification"],"prefix":"10.1007","volume":"9","author":[{"given":"Jan","family":"Bakus","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamed S.","family":"Kamel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2005,9,9]]},"reference":[{"issue":"3","key":"209_CR1","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/183422.183423","volume":"12","author":"C Apt\u00e9","year":"1994","unstructured":"Apt\u00e9 C, Damerau F, Weiss SM (1994) Automated learning of decision rules for text categorization. ACM Trans Inform Syst (TOIS) 12(3):233\u2013251","journal-title":"ACM Trans Inform Syst (TOIS)"},{"key":"209_CR2","unstructured":"Bakus J, Kamel M (2003) Information theoretic feature selection for document classification. In: Proceedings of the Eighth Canadian Workshop on Information Theory, pp 147\u2013150. Waterloo, Ontario, Canada"},{"issue":"4","key":"209_CR3","doi-asserted-by":"crossref","first-page":"537","DOI":"10.1109\/72.298224","volume":"5","author":"R Battiti","year":"1994","unstructured":"Battiti R (1994) Using mutual information for selecting features in supervised neural net learning. IEEE Trans Neural Netw 5(4):537\u2013550","journal-title":"IEEE Trans Neural Netw"},{"key":"209_CR4","volume-title":"Pattern Recognition: A Statistical Approach","author":"PA Devijver","year":"1982","unstructured":"Devijver PA, Kittler J (1982) Pattern Recognition: A Statistical Approach. Prentice Hall, Englewood Cliffs, NJ, USA"},{"issue":"2\/3","key":"209_CR5","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1023\/A:1007413511361","volume":"29","author":"P Domingos","year":"1997","unstructured":"Domingos P, Pazzani M (1997) On the optimality of the simple Bayesian classifier under zero-one loss. Mach Learning 29 (2\/3):103\u2013130","journal-title":"Mach Learning"},{"key":"209_CR6","volume-title":"Pattern Classification","year":"2001","unstructured":"Duda RO, Hart PE, Stork DG (eds) (2001) Pattern Classification, 2nd ed. Wiley, New York","edition":"2nd ed."},{"key":"209_CR7","doi-asserted-by":"crossref","unstructured":"Dumais ST, Platt J, Heckerman D, Sahami M (1998) Inductive learning algorithms and representations for text categorization. In: Proceedings of the Seventh International Conference on Information and Knowledge Management (CIKM-98), pp 148\u2013155. Bethesda, MD, USA","DOI":"10.1145\/288627.288651"},{"key":"209_CR8","volume-title":"Transmission of Information: A Statistical Theory of Communication","author":"RM Fano","year":"1961","unstructured":"Fano RM (1961) Transmission of Information: A Statistical Theory of Communication. MIT Press, Cambridge, MA"},{"key":"209_CR9","first-page":"1289","volume":"3","author":"G Forman","year":"2003","unstructured":"Forman G (2003) An extensive empirical study of feature selection metrics for text classification. J Mach Learn Res 3:1289\u20131305","journal-title":"J Mach Learn Res"},{"key":"209_CR10","volume-title":"Theory of Psychological Measurement","author":"EE Ghiselli","year":"1964","unstructured":"Ghiselli EE (1964) Theory of Psychological Measurement. McGraw Hill, New York"},{"key":"209_CR11","unstructured":"Hall MA (2000) Correlation-based feature selection for discrete and numeric class machine learning. In: Proceedings of the 16th International Conference on Machine Learning (ICML-99), pp 359\u2013366. Stanford, CA, USA"},{"key":"209_CR12","unstructured":"Joachims T (1997) A probabilistic analysis of the Rocchio algorithm with TFIDF for text categorization. In: Proceedings of the 14th International Conference on Machine Learning (ICML-97), pp 143\u2013151. Nashville, TN, USA,"},{"key":"209_CR13","doi-asserted-by":"crossref","unstructured":"Joachims T (2001) A statistical learning model for text classification with support vector machines. In: Proceedings of the 24th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-01), pp 128\u2013136. New Orleans, LA, USA","DOI":"10.1145\/383952.383974"},{"key":"209_CR14","doi-asserted-by":"crossref","unstructured":"Ko Y, Seo J (2000) Automatic text categorization by unsupervised learning. In: Proceedings of the 18th International Conference on Computational Linguistics (COLING-00), pp 453\u2013459. Saarbr\u00fccken, Germany","DOI":"10.3115\/990820.990886"},{"issue":"1\u20132","key":"209_CR15","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/S0004-3702(97)00043-X","volume":"97","author":"R Kohavi","year":"1997","unstructured":"Kohavi R, John G (1997) Wrappers for feature subset selection. Artif Intell J 97(1\u20132):273\u2013324","journal-title":"Artif Intell J"},{"key":"209_CR16","unstructured":"Koller D, Sahami M (1996) Toward optimal feature selection. In: Proceedings of the 13th International Conference on Machine Learning (ICML-96), pp 170\u2013178. Bari, Italy"},{"issue":"1","key":"209_CR17","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1109\/72.977291","volume":"13","author":"N Kwak","year":"1994","unstructured":"Kwak N, Choi C-H (1994) Input feature selection for classification problems. IEEE Trans Neural Netw 13(1):143\u2013159","journal-title":"IEEE Trans Neural Netw"},{"key":"209_CR18","doi-asserted-by":"crossref","unstructured":"Lewis DD (1992) An evaluation of phrasal and clustered representations on a text categorization task. In: Proceedings of the 15th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-92), pp 37\u201350. Copenhagen, Denmark","DOI":"10.1145\/133160.133172"},{"key":"209_CR19","unstructured":"Lewis DD (1992) Representation and learning in information retrieval. PhD Thesis, Department of Computer and Information Science, University of Massachusetts, Amherst, MA, USA"},{"key":"209_CR20","doi-asserted-by":"crossref","unstructured":"Lewis DD, Schapire RE, Callan JP, Papka R (1996) Training algorithms for linear text classifiers. In: Proceedings of the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-96), pp 307\u2013315. Zurich, Switzerland","DOI":"10.1145\/243199.243277"},{"key":"209_CR21","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-5689-3","volume-title":"Feature Selection for Knowledge Discovery and Data Mining","author":"H Liu","year":"1998","unstructured":"Liu H, Motoda H (1998) Feature Selection for Knowledge Discovery and Data Mining. Kluwer Academic Publishers, Dordrecht"},{"key":"209_CR22","unstructured":"McCallum A, Nigam K (1998) A comparison of event models for naive Bayes text classification. In: Proceedings of the 1998 AAAI\/ICML Workshop on Learning for Text Categorization, pp 41\u201348. Madison, WI, USA"},{"key":"209_CR23","unstructured":"Mladeni\u0107 D, Grobelnik M (1998) Word sequences as features in text-learning. In: Proceedings of the Seventh Electrotechnical and Computer Science Conference (ERK-98), pp 145\u2013148. Ljubljana, Slovenia"},{"key":"209_CR24","unstructured":"Mladeni\u0107 D, Grobelnik M (1999) Feature selection for unbalanced class distribution and naive Bayes. In: Proceedings of the 16th International Conference on Machine Learning (ICML-99), pp 258\u2013267. Bled, Slovenia"},{"key":"209_CR25","volume-title":"Numerical Recipes in C","author":"WH Press","year":"1988","unstructured":"Press WH, Flannery BP, Teukolski SA, Vetterling WT (1988) Numerical Recipes in C. Cambridge University Press, Cambridge, UK"},{"key":"209_CR26","volume-title":"C4.5: Programs for Machine Learning","author":"R Quinlan","year":"1993","unstructured":"Quinlan R (1993) C4.5: Programs for Machine Learning. Morgan Kaufman, San Mateo, CA, USA"},{"issue":"5","key":"209_CR27","doi-asserted-by":"crossref","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. Inform Process Manage 24(5):513\u2013523","journal-title":"Inform Process Manage"},{"issue":"11","key":"209_CR28","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G Salton","year":"1975","unstructured":"Salton G, Yang C, Wong A (1975) A vector-space model for automatic indexing. Commun ACM 18(11):613\u2013620","journal-title":"Commun ACM"},{"key":"209_CR29","doi-asserted-by":"crossref","unstructured":"Sch\u00fctze H, Hull DA, Pedersen JO (1995) A comparison of classifiers and document representations for the routing problem. In: Proceedings of the 18th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR-95), pp 229\u2013237. Seattle, WA, USA","DOI":"10.1145\/215206.215365"},{"issue":"1","key":"209_CR30","doi-asserted-by":"crossref","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 Surveys (CSUR) 34(1):1\u201347","journal-title":"ACM Comput Surveys (CSUR)"},{"issue":"2","key":"209_CR31","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1142\/S0218001488000145","volume":"2","author":"W Sidlecki","year":"1988","unstructured":"Sidlecki W, Sklanski J (1988) On automatic feature selection. Int J Pattern Recogn Artif Intell 2(2):197\u2013220","journal-title":"Int J Pattern Recogn Artif Intell"},{"issue":"2","key":"209_CR32","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/0306-4573(81)90029-7","volume":"17","author":"CJ van Rijsbergen","year":"1981","unstructured":"van Rijsbergen CJ, Harper DJ, Porter MF (1981) The selection of good search terms. Inform Process Manage 17(2):77\u201391","journal-title":"Inform Process Manage"},{"key":"209_CR33","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V Vapnik","year":"1995","unstructured":"Vapnik V (1995) The Nature of Statistical Learning Theory. Springer, Berlin Heidelberg New York"},{"key":"209_CR34","unstructured":"Yang Y, Pedersen JP (1997) A comparative study on feature selection in text categorization. In: Proceedings of the 14th International Conference on Machine Learning (ICML-97), pp 412\u2013420. Nashville, TN, USA"},{"key":"209_CR35","doi-asserted-by":"crossref","unstructured":"Yang Y, Slattery S, Ghani R (2002) A study of approaches to hypertext categorization. J Intell Inform Syst 18(2)","DOI":"10.1023\/A:1013685612819"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-005-0209-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10115-005-0209-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-005-0209-6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T10:16:22Z","timestamp":1586427382000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10115-005-0209-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,9,9]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2006,4]]}},"alternative-id":["209"],"URL":"https:\/\/doi.org\/10.1007\/s10115-005-0209-6","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2005,9,9]]}}}