{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T13:46:23Z","timestamp":1774014383406,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2014,8,22]],"date-time":"2014-08-22T00:00:00Z","timestamp":1408665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1007\/s10044-014-0408-4","type":"journal-article","created":{"date-parts":[[2014,8,21]],"date-time":"2014-08-21T06:47:38Z","timestamp":1408603658000},"page":"369-383","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Term frequency combined hybrid feature selection method for spam filtering"],"prefix":"10.1007","volume":"19","author":[{"given":"Yuanning","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lizhou","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodong","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,8,22]]},"reference":[{"key":"408_CR1","unstructured":"Androutsopoulos I, Koutsias J, Chandrinos KV, Paliouras G, Spyropoulos C (2000) An evaluation of naive Bayesian anti-spam filtering. InL Proceedings of the workshop on machine learning in the new information age"},{"issue":"5","key":"408_CR2","doi-asserted-by":"crossref","first-page":"4760","DOI":"10.1016\/j.eswa.2011.09.160","volume":"39","author":"N Azam","year":"2012","unstructured":"Azam N, Yao J (2012) Comparison of term frequency and document frequency based feature selection metrics in text categorization. Expert Syst Appl 39(5):4760\u20134768","journal-title":"Expert Syst Appl"},{"issue":"1","key":"408_CR3","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.knosys.2011.01.015","volume":"25","author":"P Bermejo","year":"2012","unstructured":"Bermejo P, Ossa L, G\u00e1mez JA, Puerta JM (2012) Fast wrapper feature subset selection in high-dimensional datasets by means of filter re-ranking. Knowl-Based Syst 25(1):35\u201344","journal-title":"Knowl-Based Syst"},{"issue":"10","key":"408_CR4","doi-asserted-by":"crossref","first-page":"3676","DOI":"10.1016\/j.patcog.2012.04.015","volume":"45","author":"A Boubezoul","year":"2012","unstructured":"Boubezoul A, Paris S (2012) Application of global optimization methods to model and feature selection. Pattern Recogn 45(10):3676\u20133686","journal-title":"Pattern Recogn"},{"key":"408_CR5","volume-title":"Classification and regression trees","author":"L Breiman","year":"1984","unstructured":"Breiman L, Friedman JH, Olshen RA (1984) Classification and regression trees. Wadsworth International Group, Monterey"},{"issue":"1","key":"408_CR6","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.eswa.2007.09.008","volume":"36","author":"CM Chen","year":"2009","unstructured":"Chen CM, Lee HM, Chang YJ (2009) Two novel feature selection approaches for web page classification. Expert Syst Appl 36(1):260\u2013272","journal-title":"Expert Syst Appl"},{"issue":"3","key":"408_CR7","doi-asserted-by":"crossref","first-page":"5432","DOI":"10.1016\/j.eswa.2008.06.054","volume":"36","author":"JN Chen","year":"2009","unstructured":"Chen JN, Huang HK, Tian SF, Qu YL (2009) Feature selection for text classification with Na\u00efve Bayes. Expert Syst Appl 36(3):5432\u20135435","journal-title":"Expert Syst Appl"},{"key":"408_CR8","doi-asserted-by":"crossref","unstructured":"Clark J, Koprinska I, Poon J (2003) A neural network based approach to automated e-mail classification. In: Proceedings of the IEEE\/WIC international conference on web intelligence (WI 03)","DOI":"10.1109\/WI.2003.1241300"},{"key":"408_CR9","doi-asserted-by":"crossref","unstructured":"Cormack GV (2007) TREC 2007 spam track overview. In: Proceedings of TREC 2007: the 16th text retrieval conference","DOI":"10.6028\/NIST.SP.500-274.spam-overview"},{"issue":"1","key":"408_CR10","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.neucom.2006.07.007","volume":"70","author":"RF Correa","year":"2006","unstructured":"Correa RF, Ludermir TB (2006) Improving self-organization of document collections by semantic mapping. Neurocomputing 70(1):62\u201369","journal-title":"Neurocomputing"},{"issue":"8","key":"408_CR11","doi-asserted-by":"crossref","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"27","author":"T Fawcett","year":"2006","unstructured":"Fawcett T (2006) An introduction to ROC analysis. Pattern Recogn Lett 27(8):861\u2013874","journal-title":"Pattern Recogn Lett"},{"key":"408_CR12","doi-asserted-by":"crossref","unstructured":"Forman G (2008) BNS feature scaling: an improved representation over TFIDF for SVM text classification. In: Proceedings of the ACM conference on information and knowledge management. ACM, New York, pp 263\u2013279","DOI":"10.1145\/1458082.1458119"},{"issue":"3","key":"408_CR13","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1016\/j.csda.2011.09.023","volume":"56","author":"JC Gomez","year":"2012","unstructured":"Gomez JC, Moens MF (2012) PCA document reconstruction for email classification. Comput Stat Data Anal 56(3):741\u2013751","journal-title":"Comput Stat Data Anal"},{"issue":"7","key":"408_CR14","doi-asserted-by":"crossref","first-page":"10206","DOI":"10.1016\/j.eswa.2009.02.037","volume":"36","author":"TS Guzella","year":"2009","unstructured":"Guzella TS, Caminhas WM (2009) A review of machine learning approaches to spam filtering. Expert Syst Appl 36(7):10206\u201310222","journal-title":"Expert Syst Appl"},{"issue":"1","key":"408_CR15","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.ipm.2004.08.006","volume":"42","author":"C Lee","year":"2006","unstructured":"Lee C, Lee GG (2006) Information gain and divergence-based feature selection for machine learning-based text categorization. Inf Process Manag 42(1):155\u2013165","journal-title":"Inf Process Manag"},{"issue":"2","key":"408_CR16","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S1672-6529(11)60020-6","volume":"8","author":"Y Liu","year":"2011","unstructured":"Liu Y, Wang G, Chen H, Dong H, Zhu X, Wang S (2011) An improved particle swarm optimization for feature selection. J Bionic Eng 8(2):191\u2013200","journal-title":"J Bionic Eng"},{"key":"408_CR17","doi-asserted-by":"crossref","unstructured":"L\u00f3pez FR, Jim\u00e9nez-Salazar H, Pinto D (2007) A competitive term selection method for information retrieval. In: Proceedings of 8th international conference on computational linguistics and intelligent text processing, (CICLing\u201907), Lecture notes in computer science, vol 4394, pp 468\u2013475","DOI":"10.1007\/978-3-540-70939-8_41"},{"key":"408_CR18","unstructured":"McCallum A, Nigam K (2007) A comparison of event models for naive Bayes text classification. In: EACL \u201803 Proceedings of the tenth conference on European chapter of the Association for Computational Linguistics, vol 1, pp 307\u2013314"},{"issue":"5","key":"408_CR19","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1002\/asi.21023","volume":"60","author":"SSR Mengle","year":"2009","unstructured":"Mengle SSR, Goharian N (2009) Ambiguity measure feature selection algorithm. J Am Soc Inform Sci Technol 60(5):1037\u20131050","journal-title":"J Am Soc Inform Sci Technol"},{"issue":"1","key":"408_CR20","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/S0167-9236(02)00097-0","volume":"35","author":"D Mladenic","year":"2003","unstructured":"Mladenic D, Grobelnik M (2003) Feature selection on hierarchy of web documents. Decis Support Syst 35(1):45\u201387","journal-title":"Decis Support Syst"},{"issue":"3","key":"408_CR21","doi-asserted-by":"crossref","first-page":"6826","DOI":"10.1016\/j.eswa.2008.08.006","volume":"36","author":"H Ogura","year":"2009","unstructured":"Ogura H, Amano H, Kondo M (2009) Feature selection with a measure of deviations from poisson in text categorization. Expert Syst Appl 36(3):6826\u20136832","journal-title":"Expert Syst Appl"},{"key":"408_CR22","first-page":"81","volume":"1","author":"JR Quinlan","year":"1986","unstructured":"Quinlan JR (1986) Induction of decision trees. Mach Learn 1:81\u2013106","journal-title":"Mach Learn"},{"issue":"12","key":"408_CR23","doi-asserted-by":"crossref","first-page":"11094","DOI":"10.1016\/j.eswa.2012.03.061","volume":"39","author":"R Ruiz","year":"2012","unstructured":"Ruiz R, Riquelme JC, Aguilar-Ruiz JS, Garc\u00eda-Torres M (2012) Fast feature selection aimed at high-dimensional data via hybrid-sequential-ranked searches. Expert Syst Appl 39(12):11094\u201311102","journal-title":"Expert Syst Appl"},{"key":"408_CR24","doi-asserted-by":"crossref","unstructured":"Salton G, Clement TY (1973) On the construction of effective vocabularies for information retrieval. In: Proceedings of the 1973 meeting on programming languages and information retrieval. ACM, New York, pp 48\u201360","DOI":"10.1145\/951762.951766"},{"key":"408_CR25","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G Salton","year":"1975","unstructured":"Salton G, Wong A, Yang C (1975) A vector space model for automatic indexing. Commun ACM 18:613\u2013620","journal-title":"Commun ACM"},{"issue":"1","key":"408_CR26","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1016\/j.eswa.2011.07.034","volume":"39","author":"I Santos","year":"2012","unstructured":"Santos I, Laorden C, Sanz B, Bringas PG (2012) Enhanced topic-based vector space model for semantics-aware spam filtering. Expert Syst Appl 39(1):437\u2013444","journal-title":"Expert Syst Appl"},{"issue":"1","key":"408_CR27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.eswa.2006.04.001","volume":"33","author":"W Shang","year":"2007","unstructured":"Shang W, Huang H, Zhu H, Lin Y, Qu Y, Wang Z (2007) A novel feature selection algorithm for text categorization. Expert Syst Appl 33(1):1\u20135","journal-title":"Expert Syst Appl"},{"key":"408_CR28","unstructured":"SpamAssassin (2005) Spamassassin public corpus. http:\/\/spamassassin.apache.org\/publiccorpus\/ . Accessed June 2008"},{"key":"408_CR29","unstructured":"Tezel SK (2009) Improving SVM classification on imbalanced data sets in distance space. Ninth IEEE international conference on data mining"},{"key":"408_CR30","unstructured":"Tretyakov K (2004) Machine learning techniques in spam filtering. Data mining problem-oriented seminar MTAT.03.177, pp 60\u201379"},{"issue":"3","key":"408_CR31","first-page":"219","volume":"40","author":"P Willett","year":"2006","unstructured":"Willett P (2006) The Porter stemming algorithm: then and now. Progr Electron Libr Inf Syst 40(3):219\u2013223","journal-title":"Progr Electron Libr Inf Syst"},{"key":"408_CR32","doi-asserted-by":"crossref","unstructured":"Yan J, Liu N, Zhang B, Yan S, Chen Z, Cheng Q (2005) OCFS: optimal orthogonal centroid feature selection for text categorization. In: Proceedings of the 28th annual international ACM Sinformation gainIR conference on research and development in information retrieval, ACM, New York, pp 122\u2013129","DOI":"10.1145\/1076034.1076058"},{"issue":"6","key":"408_CR33","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1016\/j.knosys.2011.04.006","volume":"24","author":"J Yang","year":"2011","unstructured":"Yang J, Liu Y, Liu Z, Zhu X, Zhang X (2011) A new feature selection algorithm based on binomial hypothesis testing for spam filtering. Knowl-Based Syst 24(6):904\u2013914","journal-title":"Knowl-Based Syst"},{"issue":"4","key":"408_CR34","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1016\/j.ipm.2011.12.005","volume":"48","author":"J Yang","year":"2012","unstructured":"Yang J, Liu Y, Zhu X, Liu Z, Zhang X (2012) A new feature selection based on comprehensive measurement both in inter-category and intra-category for text categorization. Inf Process Manag 48(4):741\u2013754","journal-title":"Inf Process Manag"},{"key":"408_CR35","unstructured":"Yang Y, Pedersen J (1997) A comparative study on feature set selection in text categorization, In: Fisher DH (ed) Proceedings of the 14th international conference on machine learning. Morgan Kaufmann, San Francisco, pp 412\u2013420"},{"key":"408_CR36","doi-asserted-by":"crossref","unstructured":"Youn S, McLeod D (2007) A comparative study for email classification. Advances and innovations in systems, computing sciences and software engineering, pp 387\u2013391","DOI":"10.1007\/978-1-4020-6264-3_67"},{"issue":"4","key":"408_CR37","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.knosys.2008.01.001","volume":"21","author":"B Yu","year":"2008","unstructured":"Yu B, Xu Z (2008) A comparative study for content-based dynamic spam classification using four machine learning algorithms. Knowl-Based Syst 21(4):355\u2013362","journal-title":"Knowl-Based Syst"},{"issue":"1","key":"408_CR38","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.cmpb.2011.12.015","volume":"108","author":"SN Yu","year":"2012","unstructured":"Yu SN, Lee MY (2012) Conditional mutual information-based feature selection for congestive heart failure recognition using heart rate variability. Comput Methods Programs Biomed 108(1):299\u2013309","journal-title":"Comput Methods Programs Biomed"},{"issue":"4","key":"408_CR39","first-page":"32","volume":"101","author":"Y Zhang","year":"2012","unstructured":"Zhang Y, Li S, Wang T, Zhang Z (2012) Divergence-based feature selection for separate classes. Neurocomputing 101(4):32\u201342","journal-title":"Neurocomputing"},{"issue":"2","key":"408_CR40","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1109\/TIFS.2010.2103060","volume":"6","author":"Y Zhu","year":"2011","unstructured":"Zhu Y, Tan Y (2011) A local-concentration-based feature extraction approach for spam filtering. IEEE Trans Inf Forensics Secur 6(2):486\u2013497","journal-title":"IEEE Trans Inf Forensics Secur"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-014-0408-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10044-014-0408-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-014-0408-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T08:52:43Z","timestamp":1746348763000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10044-014-0408-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,8,22]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,5]]}},"alternative-id":["408"],"URL":"https:\/\/doi.org\/10.1007\/s10044-014-0408-4","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,8,22]]}}}