{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T09:43:20Z","timestamp":1770975800895,"version":"3.50.1"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2010,5,23]],"date-time":"2010-05-23T00:00:00Z","timestamp":1274572800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"published-print":{"date-parts":[[2010,6]]},"DOI":"10.1007\/s10462-010-9166-x","type":"journal-article","created":{"date-parts":[[2010,5,22]],"date-time":"2010-05-22T14:09:26Z","timestamp":1274537366000},"page":"73-108","source":"Crossref","is-referenced-by-count":87,"title":["A study of spam filtering using support vector machines"],"prefix":"10.1007","volume":"34","author":[{"given":"Ola","family":"Amayri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nizar","family":"Bouguila","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,5,23]]},"reference":[{"key":"9166_CR1","unstructured":"Abadi M, Burrows M, Manasse M, Wobber T (2003) Moderately hard, memory-bound functions. In: Proceedings of the 10th annual network and distributed system security symposium, California, USA, pp 25\u201339"},{"issue":"2","key":"9166_CR2","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1214\/aoms\/1177704568","volume":"33","author":"T Anderson","year":"1962","unstructured":"Anderson T, Bahadur R (1962) Classification into two multivariate normal distributions with different covariance matrices. Ann Math Stat 33(2): 420\u2013431","journal-title":"Ann Math Stat"},{"key":"9166_CR3","unstructured":"Androutsopoulos I, Koutsias J, Chandrinos K, Paliouras G, Spyropoulos C (2000a) An evaluation of naive bayesian anti-spam filtering. In: Proceedings of the 11th European conference on machine learning, Barcelona, Spain, pp 9\u201317"},{"key":"9166_CR4","unstructured":"Androutsopoulos I, Paliouras G, Karkaletsis V, Sakkis G, Spyropoulos C, Stamatopoulos P (2000b) Learning to filter spam e-mail: A comparison of a naive bayesian and a memory-based approach. In: Proceedings of the workshop on machine learning and textual information access, 4th european conference on principles and practice of knowledge discovery in databases, Lyon, France, pp 1\u201313"},{"key":"9166_CR5","unstructured":"Back A (2002) Hashcash\u2014a denial of service counter-measure. http:\/\/cypherspace.org\/hashcash\/hashcash\/.pdf"},{"key":"9166_CR6","volume-title":"Harmonic analysis on semigroups. Theory of positive definite and related functions. Graduate texts in mathematics, vol 100","author":"Ch Berg","year":"1984","unstructured":"Berg Ch, Christensen JPR, Bessel P (1984) Harmonic analysis on semigroups. Theory of positive definite and related functions. Graduate texts in mathematics, vol 100. Springer-Verlag, New York"},{"issue":"1","key":"9166_CR7","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1007\/s10462-009-9109-6","volume":"29","author":"E Blanzieri","year":"2006","unstructured":"Blanzieri E, Bryl A (2006) A survey of learning-based techniques of email spam filtering. Artif Intell Rev 29(1): 63\u201392","journal-title":"Artif Intell Rev"},{"key":"9166_CR8","unstructured":"Brinker K (2003) Incorporating diversity in active learning with support vector machines. In: Proceedings of the twentieth international conference on machine learning, pp 59\u201366"},{"key":"9166_CR9","unstructured":"Caropreso MF, Matwin S, Sebastiani F (2001) Text databases and document management: theory and practice, IGI Publishing, chap A learner-independent evaluation of the usefulness of statistical phrases for automated text categorization, pp 78\u2013102"},{"key":"9166_CR10","unstructured":"Carreras X, Marquez L (2001) Boosting trees for anti-spam email filtering. In: Proceedings of the 4th international conference on recent advances in natural language processing, Bulgaria, pp 58\u201364"},{"key":"9166_CR11","unstructured":"Cauwenberghs G, Poggio T (2000) Incremental and decremental support vector machine learning. In: Proceedings of the neural information processing systems (NIPS), pp 409\u2013415"},{"key":"9166_CR12","unstructured":"Chang EY, Tong S, Goh K, Chang C (2001) Support vector machine concept-dependent active learning for image retrieval. In: Proceedings of the ACM international conference on multimedia, pp 107\u2013118"},{"issue":"2","key":"9166_CR13","first-page":"201","volume":"15","author":"D Cohn","year":"1994","unstructured":"Cohn D, Atlas L, Ladner R (1994) Improving generalization with active learning. Mach Learn 15(2): 201\u2013221","journal-title":"Mach Learn"},{"key":"9166_CR14","unstructured":"Cormack GV, Bratko A (2006) Batch and on-line spam filter comparison. In: Proceedings of the third conference on email and anti-spam, California, USA"},{"key":"9166_CR15","doi-asserted-by":"crossref","unstructured":"Cormack GV, Lynam TR (2005) Trec 2005 spam track overview. In: Proceedings of the fourteenth text retrieval conference (TREC05), Gaithersburg, MD","DOI":"10.6028\/NIST.SP.500-266.spam-overview"},{"issue":"1","key":"9166_CR16","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(1): 273\u2013329","journal-title":"Mach Learn"},{"key":"9166_CR17","volume-title":"Methods of mathematical physics, vol 1","author":"R Courant","year":"1953","unstructured":"Courant R, Hilbert D (1953) Methods of mathematical physics, vol 1. Interscience Publishers Inc., New York"},{"key":"9166_CR18","doi-asserted-by":"crossref","unstructured":"Cranor LF, LaMacchia BA (1998) Spam! Commun ACM 41(8): 74\u201383","DOI":"10.1145\/280324.280336"},{"key":"9166_CR19","doi-asserted-by":"crossref","unstructured":"Cukier W, Cody S, Nesselroth E (2006) Genres of spam: expectations and deceptions. In: Proceeding of the 39th annual Hawaii international conference on system sciences, vol 3. Hawaii, USA","DOI":"10.1109\/HICSS.2006.195"},{"key":"9166_CR20","doi-asserted-by":"crossref","unstructured":"Debole F, Sebastiani F (2003) Supervised term weighting for automated text categorization. In: Proceedings of the ACM symposium on Applied computing, Florida, USA, pp 784\u2013788","DOI":"10.1145\/952532.952688"},{"key":"9166_CR21","unstructured":"Drake C, Oliver J, Koontz E (2004) Anatomy of a phishing email. In: Proceeding of first conference on email and anti-Spam (CEAS), California, USA"},{"issue":"5","key":"9166_CR22","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.1109\/72.788645","volume":"10","author":"H Drucker","year":"1999","unstructured":"Drucker H, Vapnik V, Wu D (1999) Support vector machines for spam categorization. IEEE Trans Neural Netw 10(5): 1048\u20131054","journal-title":"IEEE Trans Neural Netw"},{"key":"9166_CR23","unstructured":"Dwork C, Naor M (1993) Pricing via processing or combating junk mail. In: 12th annual international cryptology conference on advances in cryptology, Springer, no. 740 in LNCS, pp 139\u2013147"},{"key":"9166_CR24","volume-title":"Roc graphs: notes and practical considerations for researchers. Techanical report","author":"T Fawcett","year":"2004","unstructured":"Fawcett T (2004) Roc graphs: notes and practical considerations for researchers. Techanical report. HP Laboratories, Palo Alto, USA"},{"key":"9166_CR25","volume-title":"The road ahead","author":"B Gates","year":"1995","unstructured":"Gates B, Myhrvold N, Rinearson P (1995) The road ahead. Viking Penguin, New York"},{"key":"9166_CR26","unstructured":"Goodman J (2003) Spam: technologies and policies. http:\/\/www.research.microsoft.com\/~joshuago\/spamtech.pdf"},{"key":"9166_CR27","unstructured":"Graham P (2002) A plan for spam. http:\/\/www.paulgraham.com\/spam.html"},{"key":"9166_CR28","unstructured":"Hulten G, Goodman J (2003) Tutorial on junk mail filtering. http:\/\/research.microsoft.com\/~joshuago\/tutorialOnJunkMailFilteringjune4.pdf"},{"key":"9166_CR29","doi-asserted-by":"crossref","unstructured":"Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: N\u00e9dellec C, Rouveirol C (eds) Proceedings of of ECML-98, 10th European conference on machine learning, Springer, Chemnitz, DE, 1398, pp 137\u2013142","DOI":"10.1007\/BFb0026683"},{"key":"9166_CR30","doi-asserted-by":"crossref","unstructured":"Joachims T (1999a) Advances in kernel methods: support vector machines learning, MIT Press, Cambridge, MA, USA, chap Making large-scale support vector machine learning practical, pp 169\u2013184","DOI":"10.7551\/mitpress\/1130.003.0015"},{"key":"9166_CR31","unstructured":"Joachims T (1999b) Transductive inference for text classification using support vector machines. In: Proceedings of the sixteenth international conference on machine learning (ICML-99), San Francisco, US, pp 200\u2013209"},{"issue":"2","key":"9166_CR32","first-page":"31","volume":"3","author":"N Kasabov","year":"2004","unstructured":"Kasabov N, Pang S (2004) Transductive support vector machines and applications in bioinformatics for promoter recognition. Neural Inf Process 3(2): 31\u201338","journal-title":"Neural Inf Process"},{"issue":"8","key":"9166_CR33","doi-asserted-by":"crossref","first-page":"2165","DOI":"10.1109\/TSP.2004.830991","volume":"52","author":"J Kivinen","year":"2004","unstructured":"Kivinen J, Smola A, Williamson R (2004) Online learning with kernels. IEEE Transac Signal Process 52(8): 2165\u20132176","journal-title":"IEEE Transac Signal Process"},{"key":"9166_CR34","unstructured":"Kolcz A, Alspector J (2001) Svm-based filtering of e-mail spam with content-specific misclassification costs. In: Proceedings of the Workshop on text mining, California, USA, pp 123\u2013130"},{"issue":"8","key":"9166_CR35","doi-asserted-by":"crossref","first-page":"1913","DOI":"10.1016\/S0031-3203(03)00038-4","volume":"36","author":"KW Lau","year":"2003","unstructured":"Lau KW, Wu QH (2003) Online training of support vector machine. Pattern Recognit 36(8): 1913\u20131920","journal-title":"Pattern Recognit"},{"issue":"13","key":"9166_CR36","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1023\/A:1012491419635","volume":"46","author":"E Leopold","year":"2002","unstructured":"Leopold E, Kindermann J (2002) Text categorization with support vector machines. How to represent texts in input space?. Machine Learning 46(13): 423\u2013444","journal-title":"Machine Learning"},{"key":"9166_CR37","first-page":"1435","volume":"5","author":"C Leslie","year":"2004","unstructured":"Leslie C, Kuang R (2004) Fast string kernels using inexact matching for protein sequences. J Mach Learn Res 5: 1435\u20131455","journal-title":"J Mach Learn Res"},{"key":"9166_CR38","unstructured":"Leslie C, Eskin E, Noble WS (2002) The spectrum kernel: a string kernel for svm protein classification. In: Proceedings of the pacific symposium on biocomputing, Hawaii, USA, pp 564\u2013575"},{"key":"9166_CR39","doi-asserted-by":"crossref","unstructured":"Lewis DD (1992) An evaluation of phrasal and clustered representations on a text categorization task. In: Proceedings of the annual ACM conference on research and development in information retrieval, Copenhagen, Denmark, pp 37\u201350","DOI":"10.1145\/133160.133172"},{"issue":"1","key":"9166_CR40","first-page":"419","volume":"2","author":"H Lodhi","year":"2002","unstructured":"Lodhi H, Saunders C, Shawe-Taylor J, Cristianini N, Watkins C (2002) Text classification using string kernels. J Mach Learn Res 2(1): 419\u2013444","journal-title":"J Mach Learn Res"},{"key":"9166_CR41","unstructured":"Lugaresi N (2004) European union vs. spam: a legal response. In: Proceeding of first conference on email and anti-Spam (CEAS), California, USA"},{"key":"9166_CR42","doi-asserted-by":"crossref","unstructured":"Nagamalai C, Dhinakaran D, Lee JK (2007) Multi layer approach to defend ddos attacks caused by spam. In: Proceedings of the international conference on multimedia and ubiquitous engineering, Washington, DC, USA, pp 97\u2013102","DOI":"10.1109\/MUE.2007.157"},{"issue":"3","key":"9166_CR43","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"M Porter","year":"1980","unstructured":"Porter M (1980) An algorithm for suffix stripping. Program 14(3): 130\u2013137","journal-title":"Program"},{"key":"9166_CR44","unstructured":"Rocchio J (1971) Relevance feedback in information retrieval. In: Proceedings of the SMART retrieval system: expriments in automatic document processing, New Jersey, USA, pp 313\u2013323"},{"key":"9166_CR45","unstructured":"Roy N, McCallum A (2001) Toward optimal active learning through sampling estimation of error reduction. In: Proceedings of the eighteenth international conference on machine learning, pp 441\u2013448"},{"key":"9166_CR46","doi-asserted-by":"crossref","unstructured":"R\u00e4tsch G, Sonnenburg S (2004) Kernel methods in computational biology, MIT Press, chap Accurate Splice Site Detection for Caenorhabditis elegans","DOI":"10.7551\/mitpress\/4057.003.0018"},{"issue":"1","key":"9166_CR47","doi-asserted-by":"crossref","first-page":"i369","DOI":"10.1093\/bioinformatics\/bti1053","volume":"21","author":"G R\u00e4tsch","year":"2005","unstructured":"R\u00e4tsch G, Sonnenburg S, Sch\u00f6lkopf B (2005) Rase: recognition of alternatively spliced exons in c. elegans. Bioinformatics 21(1): i369\u2013i377","journal-title":"Bioinformatics"},{"key":"9166_CR48","doi-asserted-by":"crossref","unstructured":"Ruping S (2001) Incremental learning with support vector machines. In: Proceedings of the 2001 IEEE international conference on data mining, Washington, DC, USA, pp 641\u2013642","DOI":"10.1109\/ICDM.2001.989589"},{"issue":"1","key":"9166_CR49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1108\/eb026671","volume":"35","author":"G Salton","year":"1979","unstructured":"Salton G (1979) Mathematics and information retrival. J Doc 35(1): 1\u201329","journal-title":"J Doc"},{"issue":"3","key":"9166_CR50","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1090\/S0002-9947-1938-1501980-0","volume":"44","author":"IJ Schoenberg","year":"1938","unstructured":"Schoenberg IJ (1938) Metric spaces and positive definite functions. Trans Am Math Soc 44(3): 522\u2013536","journal-title":"Trans Am Math Soc"},{"key":"9166_CR51","unstructured":"Schohn G, Cohn D (2000) Less is more: active learning with support vector machines. In: Proceedings of the seventeenth international conference on machine learning, California, USA, pp 839\u2013846"},{"key":"9166_CR52","unstructured":"Scholkopf B (2000) The kernel trick for distances. In: Proceedings of the advances in neural information processing systems (NIPS), Colorado, USA, pp 301\u2013307"},{"key":"9166_CR53","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","volume-title":"Learning with kernels: support vector machines, regularization, optimization, and beyond","author":"B Scholkopf","year":"2001","unstructured":"Scholkopf B, Smola A (2001) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge, MA"},{"key":"9166_CR54","unstructured":"Sculley D (2007) Online active learning methods for fast label-efficient spam filtering. In: Proceedings of the fourth conference on email and anti-Spam (CEAS 2007), Berlin, Germany"},{"key":"9166_CR55","doi-asserted-by":"crossref","unstructured":"Sculley D, Wachman G (2007) Relaxed online svms for spam filtering. In: Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval, Amsterdam, Netherlands, pp 415\u2013422","DOI":"10.1145\/1277741.1277813"},{"issue":"1","key":"9166_CR56","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 Surv 34(1): 1\u201347","journal-title":"ACM Comput Surv"},{"key":"9166_CR57","unstructured":"SpamAssassin (2008) http:\/\/spamassassin.apache.org\/tests"},{"key":"9166_CR58","unstructured":"SPAMHAUS (2003) The spam definition and legalization game. http:\/\/www.spamhaus.org\/news.lasso?article=9 , Accessed: 31.05.07"},{"key":"9166_CR59","unstructured":"Szummer M, Jaakkola T (2003) Information regularization with partially labeled data. In: Proceedings of the advances in neural information processing systems (NIPS), British Columbia, Canada"},{"key":"9166_CR60","volume-title":"Statistical learning theory","author":"V Vapnik","year":"1998","unstructured":"Vapnik V (1998) Statistical learning theory. Wiley-Interscience, New York"},{"issue":"1","key":"9166_CR61","first-page":"1867","volume":"8","author":"J Wang","year":"2006","unstructured":"Wang J, Shen X (2006) Large margin semi-supervised learning. J Mach Learn Res 8(1): 1867\u20131891","journal-title":"J Mach Learn Res"},{"key":"9166_CR62","unstructured":"Wittel G, Wu S (2004) On attacking statistical spam filters. In: Proceedings of the first conference on email and anti-spam (CEAS), California, USA"},{"key":"9166_CR63","doi-asserted-by":"crossref","unstructured":"Xu C, Zhou Y (2007) Transductive support vector machine for personal inboxes spam categorization. In: Proceedings of the international conference on computational intelligence and security workshops, Washington, DC, USA, pp 459\u2013463","DOI":"10.1109\/CISW.2007.4425533"},{"key":"9166_CR64","doi-asserted-by":"crossref","unstructured":"Zhang D, Sun lee W (2006) Extracting key-substring-group features for text classfication. In: Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining, Pennsylvania, USA, pp 474\u2013483","DOI":"10.1145\/1150402.1150455"},{"key":"9166_CR65","unstructured":"Zhu X, Ghahramani Z, Lafferty J (2003) Semi-supervised learning using gaussian fields and harmonic functions. In: Proceedings of the twentieth international conference on machine learning (ICML), Washington, DC, USA, pp 912\u2013919"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-010-9166-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10462-010-9166-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-010-9166-x","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T02:17:57Z","timestamp":1740104277000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10462-010-9166-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5,23]]},"references-count":65,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2010,6]]}},"alternative-id":["9166"],"URL":"https:\/\/doi.org\/10.1007\/s10462-010-9166-x","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"value":"0269-2821","type":"print"},{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2010,5,23]]}}}