@book{Ott93, author = "R. Lyman Ott", title = "An Introduction to Statistical Methods and Data Analysis", year = "1993", publisher = "Duxbury Press", address = "Belmont, California" } @inproceedings{ Cohen96, author = "William W. Cohen", title = "Learning Rules that Classify E-Mail", booktitle = "AAAI Spring Symposium on Machine Learning in Information Access", year = "1996" } @inproceedings{ Sahami98, author = "Mehran Sahami and Susan Dumais and David Heckerman and Eric Horvitz", title = "A Bayesian Approach to Filtering Junk {E}-Mail", booktitle = "Learning for Text Categorization: Papers from the 1998 Workshop", publisher = "AAAI Technical Report WS-98-05", address = "Madison, Wisconsin", year = "1998", url = "citeseer.nj.nec.com/sahami98bayesian.html" } @inproceedings{ Pantel98, author = "Patrick Pantel and Dekang Lin", title = "SpamCop: {A} Spam Classification \& Organization Program", booktitle = "Learning for Text Categorization: Papers from the 1998 Workshop", publisher = "AAAI Technical Report WS-98-05", address = "Madison, Wisconsin", year = "1998", url = "citeseer.nj.nec.com/pantel98spamcop.html" } @inproceedings{ Schapire98, author = "Robert E. Schapire and Yoram Singer", title = "Improved Boosting Algorithms using Confidence-Rated Predictions", booktitle = "Proceedings of the Eleventh Annual Conference on Computational Learning Theory", pages = "80-91", year = "1998", url = "citeseer.nj.nec.com/schapire99improved.html" } @misc{ Platt98, author = "John C. Platt", title = "Sequential minimal optimization: A fast algorithm for training support vector machines", text = "Technical Report 98-14, Microsoft Research, Redmond, Washington", year = "1998", url = "citeseer.nj.nec.com/platt98sequential.html" } @Article{Drucker99, author = "Harris Drucker and Vladimir Vapnik and Dongui Wu", year = "1999", title = "Support Vector Machines for Spam Categorization", journal = "IEEE Transactions on Neural Networks", volume = "10", number = "5", pages = "1048--1054", URL = "http://www.monmouth.edu/~drucker/SVM_spam_article_compete.PDF", } @inproceedings{ Schapire99, author = "Robert E. Schapire", title = "A Brief Introduction to Boosting", booktitle = "Proceedings of the International Joint Conference on Artificial Intelligence", pages = "1401-1406", year = "1999", url = "citeseer.nj.nec.com/schapire99brief.html" } @InProceedings{Androutsopoulos00c, author = "I. Androutsopoulos and J. Koutsias and K. V. Chandrinos and G. Paliouras and C. D. Spyropoulos", year = "2000", title = "An Evaluation of Naive Bayesian Anti-Spam Filtering", booktitle = "Proceedings of the Workshop on Machine Learning in the New Information Age, 11th European Conference on Machine Learning (ECML 2000)", pages = "9--17", address = "Barcelona, Spain", URL = "http://arXiv.org/abs/cs.CL/0006013", } @InProceedings{Androutsopoulos00b, author = "I. Androutsopoulos and G. Paliouras and V. Karkaletsis and G. Sakkis and C. D. Spyropoulos and P. Stamatopoulos", year = "2000", title = "Learning to Filter Spam {E}-Mail: {A} Comparison of a Naive Bayesian and a Memory-Based Approach", booktitle = "Proceedings of the Workshop on Machine Learning and Textual Information Access, 4th European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD 2000)", pages = "1--13", address = "Lyon, France", URL = "http://arXiv.org/abs/cs/0009009", } @InProceedings{Androutsopoulos00a, author = "Ion Androutsopoulos and John Koutsias and Konstandinos V. Chandrinos and Constantine D. Spyropoulos", year = "2000", title = "An experimental comparison of naive {B}ayesian and keyword-based anti-spam filtering with personal e-mail messages", booktitle = "Proceedings of SIGIR-00, 23rd ACM International Conference on Research and Development in Information Retrieval", pages = "160--167", publisher = "ACM Press, New York, US", address = "Athens, GR", URL = "http://www.acm.org/pubs/articles/proceedings/ir/345508/p160-androutsopoulos/p160-androutsopoulos.pdf", } @InProceedings{Hidalgo00, author = "J. M. G{\'o}mez Hidalgo and M. Ma{\~n}a L{\'o}pez and E. Puertas Sanz", year = "2000", title = "Combining Text and Heuristics for Cost-Sensitive Spam Filtering", booktitle = "Proceedings of the Fourth Computational Natural Language Learning Workshop, CoNLL-2000", publisher = "Association for Computational Linguistics", address = "Lisbon, Portugal", URL = "http://www.esi.uem.es/~jmgomez/spam/Gomez00.zip", } @inproceedings{ Pazzani00, author = "Michael J. Pazzani", title = "Representation of electronic mail filtering profiles: a user study", booktitle = "Intelligent User Interfaces", pages = "202-206", year = "2000", url = "citeseer.nj.nec.com/pazzani00representation.html" } @inproceedings{ Rennie00, author = "Jason D. M. Rennie", title = "{i}file: An Application of Machine Learning to Mail Filtering", booktitle = "Proceedings of the KDD-2000 Workshop on Text Mining", year = 2000, url = "citeseer.nj.nec.com/rennie00ifile.html" } @inproceedings{ Diao00, author = "Yanlei Diao and Hongjun Lu and Dekai Wu", title = "A comparative study of classification-based personal e-mail filtering", booktitle = "Proceedings of {PAKDD}-00, 4th Pacific-Asia Conference on Knowledge Discovery and Data Mining", publisher = "Springer Verlag, Heidelberg, DE", address = "Kyoto, JP", pages = "408--419", year = "2000", url = "citeseer.nj.nec.com/diao00comparative.html" } @book{Witten00, author = "Ian H. Witten and Eibe Frank", title = "Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations", year = "2000", publisher = "Morgan Kaufmann" } @inproceedings{ Carreras01, author = "Xavier Carreras and Llu\'{\i}s M\'arquez", title = "Boosting Trees for Anti-Spam Email Filtering", booktitle = "Proceedings of {RANLP}-01, 4th International Conference on Recent Advances in Natural Language Processing", address = "Tzigov Chark, BG", year = "2001", url = "citeseer.nj.nec.com/article/carreras01boosting.html" } @InProceedings{Sakkis01, author = "Georgios Sakkis and Ion Androutsopoulos and Georgios Paliouras and Vangelis Karkaletsis and Constantine D. Spyropoulos and Panagiotis Stamatopoulos", year = "2001", title = "Stacking Classifiers for Anti-Spam Filtering of {E}-Mail", booktitle = "Proceedings of EMNLP-01, 6th Conference on Empirical Methods in Natural Language Processing", publisher = "Association for Computational Linguistics, Morristown, US", address = "Pittsburgh, US", URL = "http://www.arxiv.org/abs/cs.CL/0106040", } @INPROCEEDINGS{Kolcz01, author = {Aleksander Kolcz and Joshua Alspector}, year = 2001, title = {{SVM}-based Filtering of E-mail Spam with Content-specific Misclassification Costs}, booktitle = {Proceedings of the TextDM'01 Workshop on Text Mining - held at the 2001 IEEE International Conference on Data Mining}, url = {http://www-ai.ijs.si/DunjaMladenic/TextDM01/papers/Kolcz_TM.pdf} } @InProceedings{Hidalgo02, author = "Jose M. {G{\'o}mez Hidalgo}", year = "2002", title = "Evaluating Cost-Sensitive Unsolicited Bulk Email Categorization", booktitle = "Proceedings of SAC-02, 17th ACM Symposium on Applied Computing", pages = "615--620", address = "Madrid, ES", URL = "http://www.esi.uem.es/~jmgomez/spam/Gomez02.zip", } @inproceedings{ Soonthornphisaj02, author = "Nuanwan Soonthornphisaj and Kanokwan Chaikulseriwat and Piyanan Tang-on", title = "Anti-Spam Filtering: A Centroid-based Classification Approach", booktitle = "Proceedings of the International Conference on Signal Processing (ICSP' 02)", address = "Beijing, China", year = "2002" } @inproceedings{Li02, author = "Kun-Lun Li and Kai Li and Hou-Kuan Huang and Sheng-Feng Tian", title = "Active learning with simplified SVMs for spam categorization", booktitle = "Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC02)", year = "2002", pages = "1198--1202", address = "Beijing, China" } @Article{Cristianini02, author = "Nello Cristianini and Bernhard Schoelkopf", year = "2002", title = "Support Vector Machines and Kernel Methods, The New Generation of Learning Machines", journal = "Artificial Intelligence Magazine", volume = "23", number = "3", pages = "31--41" } @inproceedings{Schneider03, author = "Karl-Michael Schneider", title = "A Comparison of Event Models for Naive Bayes Anti-Spam E-mail Filtering", year = 2003, booktitle = "Proceedings of the 10th Conference of the European Chapter of the Association for Computational Linguistics", url = "citeseer.nj.nec.com/schneider03comparison.html" }