{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:42:25Z","timestamp":1750308145914,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2005,8,21]],"date-time":"2005-08-21T00:00:00Z","timestamp":1124582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2005,8,21]]},"DOI":"10.1145\/1081870.1081885","type":"proceedings-article","created":{"date-parts":[[2005,11,7]],"date-time":"2005-11-07T17:34:39Z","timestamp":1131384879000},"page":"98-107","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Combining email models for false positive reduction"],"prefix":"10.1145","author":[{"given":"Shlomo","family":"Hershkop","sequence":"first","affiliation":[{"name":"Columbia University, New York, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Salvatore J.","family":"Stolfo","sequence":"additional","affiliation":[{"name":"Columbia University, New York, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2005,8,21]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Androutsopoulos I. Koutsias J. Chandrinos K. Paliouras G. and Spyropoulos C. An Evauation of Na\u00efve Bayesian Anti-Spam Filtering.]]  Androutsopoulos I. Koutsias J. Chandrinos K. Paliouras G. and Spyropoulos C. An Evauation of Na\u00efve Bayesian Anti-Spam Filtering.]]"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/345508.345569"},{"key":"e_1_3_2_1_3_1","volume-title":"15th International Joint Conference on Artificial Intelligence","author":"Asker L.","year":"1997","unstructured":"Asker , L. and Maclin , R ., Ensembles as a Sequence of Classifiers . in 15th International Joint Conference on Artificial Intelligence , ( Nagoya, Japan , 1997 ), 860--865.]] Asker, L. and Maclin, R., Ensembles as a Sequence of Classifiers. in 15th International Joint Conference on Artificial Intelligence, (Nagoya, Japan, 1997), 860--865.]]"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/844102.844104"},{"key":"e_1_3_2_1_5_1","volume-title":"4th International Conference on Recent Advances in Natural Language Processing, (Tzigov Chark, BG","author":"Carreras X.","year":"2001","unstructured":"Carreras , X. and Mrquez , L ., Boosting trees for anti-spam email filtering. in RANLP-01 , 4th International Conference on Recent Advances in Natural Language Processing, (Tzigov Chark, BG , 2001 ).]] Carreras, X. and Mrquez, L., Boosting trees for anti-spam email filtering. in RANLP-01, 4th International Conference on Recent Advances in Natural Language Processing, (Tzigov Chark, BG, 2001).]]"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Clemen R.T. Combining forecasts: A revew and annotated bibliography. International Journal of Forecasting 5. 559 -- 583.]]  Clemen R.T. Combining forecasts: A revew and annotated bibliography. International Journal of Forecasting 5. 559 -- 583.]]","DOI":"10.1016\/0169-2070(89)90012-5"},{"key":"e_1_3_2_1_7_1","volume-title":"Machine Learning in Information Access: AAAI Spring Symposium (SS-96-05)","author":"Cohen W.","year":"1996","unstructured":"Cohen , W. , Learning rules that classify e-mail . in Machine Learning in Information Access: AAAI Spring Symposium (SS-96-05) , ( 1996 ), 18--25.]] Cohen, W., Learning rules that classify e-mail. in Machine Learning in Information Access: AAAI Spring Symposium (SS-96-05), (1996), 18--25.]]"},{"key":"e_1_3_2_1_8_1","first-page":"843","volume":"26","author":"Damashek M.","unstructured":"Damashek , M. Gauging Similarity via N-Grams: Language-Independant Sorting, Categorization and Retrieval of Text. Science , 26 7. 843 -- 848 .]] Damashek, M. Gauging Similarity via N-Grams: Language-Independant Sorting, Categorization and Retrieval of Text. Science, 267. 843--848.]]","journal-title":"Text. Science"},{"key":"e_1_3_2_1_9_1","series-title":"Lecture Notes in Computer Science","volume-title":"Ensemble Methods in Machine Learning","author":"Dietterich T.G.","year":"1857","unstructured":"Dietterich , T.G. Ensemble Methods in Machine Learning . Lecture Notes in Computer Science , 1857 . 1--15.]] Dietterich, T.G. Ensemble Methods in Machine Learning. Lecture Notes in Computer Science, 1857. 1--15.]]"},{"volume-title":"Support Vector Machines for Spam Categorization","author":"Drucker H.","key":"e_1_3_2_1_10_1","unstructured":"Drucker , H. , Wu , D. and Vapnik , V.N . Support Vector Machines for Spam Categorization . IEEE Transactions on Neural networks, 10 (5).]] Drucker, H., Wu, D. and Vapnik, V.N. Support Vector Machines for Spam Categorization. IEEE Transactions on Neural networks, 10 (5).]]"},{"key":"e_1_3_2_1_11_1","volume-title":"Pattern classification and scene analysis","author":"Duda R.","year":"1973","unstructured":"Duda , R. and Hart , P . Pattern classification and scene analysis . John Wiley & Sons , New York , 1973 .]] Duda, R. and Hart, P. Pattern classification and scene analysis. John Wiley & Sons, New York, 1973.]]"},{"key":"e_1_3_2_1_12_1","volume-title":"A Plan For Spam","author":"Graham P.","year":"2003","unstructured":"Graham , P. A Plan For Spam , 2003 .]] Graham, P. A Plan For Spam, 2003.]]"},{"key":"e_1_3_2_1_13_1","volume-title":"Verisign","author":"Hallam-Baker P.","year":"2003","unstructured":"Hallam-Baker , P. A Plan For No Spam , Verisign , 2003 .]] Hallam-Baker, P. A Plan For No Spam, Verisign, 2003.]]"},{"key":"e_1_3_2_1_14_1","volume-title":"Using URL Clustering to Classify Spam","author":"Hershkop S.","year":"2005","unstructured":"Hershkop , S. Using URL Clustering to Classify Spam , Columbia University , 2005 .]] Hershkop, S. Using URL Clustering to Classify Spam, Columbia University, 2005.]]"},{"key":"e_1_3_2_1_15_1","unstructured":"Hershkop S. and Stolfo S.J. Identifying Spam without Peeking at the Contents. ACM Crossroads.]]  Hershkop S. and Stolfo S.J. Identifying Spam without Peeking at the Contents. ACM Crossroads.]]"},{"key":"e_1_3_2_1_16_1","volume-title":"Computer Science Dept","author":"Hershkop S.","year":"2004","unstructured":"Hershkop , S. , Wang , K. , Lee , W. and Nimeskern , O . Email Mining Toolkit Technical Manual , Computer Science Dept , Columbia University , New York , 2004 .]] Hershkop, S., Wang, K., Lee, W. and Nimeskern, O. Email Mining Toolkit Technical Manual, Computer Science Dept, Columbia University, New York, 2004.]]"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.3115\/1117601.1117623"},{"key":"e_1_3_2_1_18_1","volume-title":"Automatic Hierarchical E-Mail Classification Using Association Rules","author":"Itskevitch J.","year":"2001","unstructured":"Itskevitch , J. Automatic Hierarchical E-Mail Classification Using Association Rules , 2001 .]] Itskevitch, J. Automatic Hierarchical E-Mail Classification Using Association Rules, 2001.]]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/2074158.2074196"},{"key":"e_1_3_2_1_20_1","volume-title":"Filtering Junk E-Mail: A Performance Comparison between Genetic Programming and Naive Bayes","author":"Katirai H.","year":"1999","unstructured":"Katirai , H. Filtering Junk E-Mail: A Performance Comparison between Genetic Programming and Naive Bayes , 1999 .]] Katirai, H. Filtering Junk E-Mail: A Performance Comparison between Genetic Programming and Naive Bayes, 1999.]]"},{"key":"e_1_3_2_1_21_1","volume-title":"Email Classification with Co-Training. in CASCON 2001","author":"Kiritchenko S.","year":"2001","unstructured":"Kiritchenko , S. and Matwin , S ., Email Classification with Co-Training. in CASCON 2001 , ( 2001 ).]] Kiritchenko, S. and Matwin, S., Email Classification with Co-Training. in CASCON 2001, (2001).]]"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2003.1159950"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.667881"},{"key":"e_1_3_2_1_24_1","volume-title":"SVM-based Filtering of E-mail Spam with Content-specific Misclassification Costs. in Workshop on Text Mining (TextDM'2001)","author":"Kolcz A.","year":"2001","unstructured":"Kolcz , A. and Alspector , J ., SVM-based Filtering of E-mail Spam with Content-specific Misclassification Costs. in Workshop on Text Mining (TextDM'2001) , (San Jose, California , 2001 ).]] Kolcz, A. and Alspector, J., SVM-based Filtering of E-mail Spam with Content-specific Misclassification Costs. in Workshop on Text Mining (TextDM'2001), (San Jose, California, 2001).]]"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/243199.243276"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1006\/inco.1994.1009"},{"key":"e_1_3_2_1_27_1","volume-title":"Usenix Winter","author":"Manber U.","year":"1994","unstructured":"Manber , U. , Finding Similar Files in a Large File System . in Usenix Winter , ( San Fransisco , CA , 1994 ), 1--10.]] Manber, U., Finding Similar Files in a Large File System. in Usenix Winter, (San Fransisco, CA, 1994), 1--10.]]"},{"key":"e_1_3_2_1_28_1","volume-title":"Learning Spam: Simple Techniques for Freely-Available Software. in USENIX 2003","author":"Massey B.","year":"2003","unstructured":"Massey , B. , Thomure , M. , Budrevich , R. and Long , S ., Learning Spam: Simple Techniques for Freely-Available Software. in USENIX 2003 , ( 2003 ).]] Massey, B., Thomure, M., Budrevich, R. and Long, S., Learning Spam: Simple Techniques for Freely-Available Software. in USENIX 2003, (2003).]]"},{"key":"e_1_3_2_1_29_1","volume-title":"Machine Learning","author":"Mitchel T.","year":"1997","unstructured":"Mitchel , T. Machine Learning . McGraw-Hill , 1997 .]] Mitchel, T. Machine Learning. McGraw-Hill, 1997.]]"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36618-0_24"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/45945.214327"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007601015854"},{"key":"e_1_3_2_1_33_1","volume-title":"Rule-Learning in Classification of Email","author":"Provost J.","year":"1999","unstructured":"Provost , J. Na\u00efve-Bayes vs . Rule-Learning in Classification of Email , 1999 .]] Provost, J. Na\u00efve-Bayes vs. Rule-Learning in Classification of Email, 1999.]]"},{"key":"e_1_3_2_1_34_1","volume-title":"KDD-2000 Workshop on Text Mining","author":"Rennie J.","year":"2000","unstructured":"Rennie , J. , ifile : An Application of Machine Learning to E-mail Filtering . in KDD-2000 Workshop on Text Mining , ( 2000 ).]] Rennie, J., ifile: An Application of Machine Learning to E-mail Filtering. in KDD-2000 Workshop on Text Mining, (2000).]]"},{"key":"e_1_3_2_1_35_1","volume-title":"Chung-Kwei: a Pattern-discovery-based System for the Automatic Identification of Unsolicited E-mail Messages. in ceas","author":"Rigoutsos I.","year":"2004","unstructured":"Rigoutsos , I. and Huynh , T. , Chung-Kwei: a Pattern-discovery-based System for the Automatic Identification of Unsolicited E-mail Messages. in ceas 2004 , ( Mountain View , California , 2004).]] Rigoutsos, I. and Huynh, T., Chung-Kwei: a Pattern-discovery-based System for the Automatic Identification of Unsolicited E-mail Messages. in ceas 2004, (Mountain View, California, 2004).]]"},{"key":"e_1_3_2_1_36_1","volume-title":"AAAI-98 Workshop on Learning for Text Categorization","author":"Sahami M.","year":"1998","unstructured":"Sahami , M. , Dumais , S. , Heckerman , D. and Horvitz , E ., A Bayesian approach to filtering junk e-mail . in AAAI-98 Workshop on Learning for Text Categorization , ( 1998 ).]] Sahami, M., Dumais, S., Heckerman, D. and Horvitz, E., A Bayesian approach to filtering junk e-mail. in AAAI-98 Workshop on Learning for Text Categorization, (1998).]]"},{"key":"e_1_3_2_1_37_1","volume-title":"6th conference on Empirical Methods in Natural Language Processing (EMNLP 2001)","author":"Sakkis G.","year":"2001","unstructured":"Sakkis , G. , Androutsopolous , I. , Paliouras , G. , Karkaletsis , V. , Spyropoulos , C. and Stamatopoulos , P ., Stacking classifiers for Anti-Spam Filtering of Emails . in 6th conference on Empirical Methods in Natural Language Processing (EMNLP 2001) , ( 2001 ).]] Sakkis, G., Androutsopolous, I., Paliouras, G., Karkaletsis, V., Spyropoulos, C. and Stamatopoulos, P., Stacking classifiers for Anti-Spam Filtering of Emails. in 6th conference on Empirical Methods in Natural Language Processing (EMNLP 2001), (2001).]]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.3115\/1067807.1067848"},{"key":"e_1_3_2_1_39_1","volume-title":"Incremental Learning in SwiftFile. in 17th International Conf. on Machine Learning","author":"Segal R.B.","year":"2000","unstructured":"Segal , R.B. and Kephart , J.O ., Incremental Learning in SwiftFile. in 17th International Conf. on Machine Learning , ( San Francisco, CA , 2000 ), Morgan Kaufmann, 863--870.]] Segal, R.B. and Kephart, J.O., Incremental Learning in SwiftFile. in 17th International Conf. on Machine Learning, (San Francisco, CA, 2000), Morgan Kaufmann, 863--870.]]"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/301136.301209"},{"key":"e_1_3_2_1_41_1","unstructured":"Stolfo S.J. Hershkop S. Wang K. Nimeskern O. and Hu C.-W. A Behavior-based Approach to Securing Email Systems. Mathematical Methods Models and Architectures for Computer Networks Security.]]  Stolfo S.J. Hershkop S. Wang K. Nimeskern O. and Hu C.-W. A Behavior-based Approach to Securing Email Systems. Mathematical Methods Models and Architectures for Computer Networks Security.]]"},{"key":"e_1_3_2_1_42_1","volume-title":"Behavior Profiling of Email. in 1st NSF\/NIJ Symposium on Intelligence & Security Informatics(ISI 2003","author":"Stolfo S.J.","year":"2003","unstructured":"Stolfo , S.J. , Hershkop , S. , Wang , K. , Nimeskern , O. and Hu , C . -W ., Behavior Profiling of Email. in 1st NSF\/NIJ Symposium on Intelligence & Security Informatics(ISI 2003 ), (Tucson, Arizona , 2003 ).]] Stolfo, S.J., Hershkop, S., Wang, K., Nimeskern, O. and Hu, C.-W., Behavior Profiling of Email. in 1st NSF\/NIJ Symposium on Intelligence & Security Informatics(ISI 2003), (Tucson, Arizona, 2003).]]"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1014052.1014152"}],"event":{"name":"KDD05: The Eleventh ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","ACM Association for Computing Machinery"],"location":"Chicago Illinois USA","acronym":"KDD05"},"container-title":["Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1081870.1081885","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1081870.1081885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T16:18:37Z","timestamp":1750263517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1081870.1081885"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,8,21]]},"references-count":43,"alternative-id":["10.1145\/1081870.1081885","10.1145\/1081870"],"URL":"https:\/\/doi.org\/10.1145\/1081870.1081885","relation":{},"subject":[],"published":{"date-parts":[[2005,8,21]]},"assertion":[{"value":"2005-08-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}