{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:03:28Z","timestamp":1782317008029,"version":"3.54.5"},"publisher-location":"Berlin, Heidelberg","reference-count":54,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642222627","type":"print"},{"value":"9783642222634","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011]]},"DOI":"10.1007\/978-3-642-22263-4_2","type":"book-chapter","created":{"date-parts":[[2011,7,18]],"date-time":"2011-07-18T17:34:45Z","timestamp":1311010485000},"page":"18-37","source":"Crossref","is-referenced-by-count":55,"title":["Text Classification for Data Loss Prevention"],"prefix":"10.1007","author":[{"given":"Michael","family":"Hart","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pratyusa","family":"Manadhata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rob","family":"Johnson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1145\/345508.345569","volume-title":"SIGIR 2000: Proceedings of the 23rd annual international ACM SIGIR Conference on Research and Development in Information Retrieval","author":"I. Androutsopoulos","year":"2000","unstructured":"Androutsopoulos, I., Koutsias, J., Chandrinos, K.V., Spyropoulos, C.D.: An experimental comparison of naive bayesian and keyword-based anti-spam filtering with personal e-mail messages. In: SIGIR 2000: Proceedings of the 23rd annual international ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 160\u2013167. ACM, New York (2000)"},{"key":"2_CR2","unstructured":"Internet Archive. Brown corpus, http:\/\/www.archive.org\/details\/BrownCorpus"},{"key":"2_CR3","unstructured":"Internet Archive. Wayback machine, http:\/\/www.archive.org\/web\/web.php"},{"key":"2_CR4","unstructured":"Attardi, G., Gull, A., Sebastiani, F.: Automatic web page categorization by link and context analysis. In: Proceedings of THAI 1999, 1st European Symposium on Telematics, Hypermedia and Artificial Intelligence (1999)"},{"key":"2_CR5","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1145\/279943.279962","volume-title":"COLT 1998: Proceedings of the eleventh annual conference on Computational learning theory","author":"A. Blum","year":"1998","unstructured":"Blum, A., Mitchell, T.: Combining labeled and unlabeled data with co-training. In: COLT 1998: Proceedings of the eleventh annual conference on Computational learning theory, pp. 92\u2013100. ACM, New York (1998)"},{"issue":"2","key":"2_CR6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1145\/321160.321165","volume":"10","author":"H. Borko","year":"1963","unstructured":"Borko, H., Bernick, M.: Automatic document classification. J. ACM\u00a010(2), 151\u2013162 (1963)","journal-title":"J. ACM"},{"key":"2_CR7","unstructured":"Breiman, L., Friedman, J., Olshen, R., Stone, C.: Classification and Regression Trees. Wadsworth, Belmont (1984)"},{"issue":"3","key":"2_CR8","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s007780050061","volume":"7","author":"S. Chakrabarti","year":"1998","unstructured":"Chakrabarti, S., Dom, B., Agrawal, R., Raghavan, P.: Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies. The VLDB Journal\u00a07(3), 163\u2013178 (1998)","journal-title":"The VLDB Journal"},{"key":"2_CR9","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"N.V. Chawla","year":"2002","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. Journal of Artificial Inteligence Research\u00a016, 321\u2013357 (2002)","journal-title":"Journal of Artificial Inteligence Research"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Chawla, N.V., Japkowicz, N., Kolcz, A.: Editorial: Special issue on learning from imbalanced data sets. SIGKDD Explorer Newsletter\u00a06(1) (2004)","DOI":"10.1145\/1007730.1007733"},{"key":"2_CR11","unstructured":"Privacy\u00a0Rights Clearinghouse. Chronology of data breaches: Security breaches 2005\u2013present (August 2010), http:\/\/www.privacyrights.org\/data-breach"},{"key":"2_CR12","first-page":"18","volume-title":"In Papers from the AAAI Spring Symposium on Machine Learning in Information Access","author":"W.W. Cohen","year":"1996","unstructured":"Cohen, W.W.: Learning rules that classify e-mail. In: In Papers from the AAAI Spring Symposium on Machine Learning in Information Access, pp. 18\u201325. AAAI Press, Menlo Park (1996)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Cortes, C., Vapnik, V.: Support-vector networks. Machine Learning, 273\u2013297 (1995)","DOI":"10.1007\/BF00994018"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Transactions on Information Theory\u00a013(1) (1967)","DOI":"10.1109\/TIT.1967.1053964"},{"key":"2_CR15","unstructured":"Dyncorp. Dyncorp website, http:\/\/www.dyncorp.com"},{"key":"2_CR16","unstructured":"Wikimedia Foundation. Wikipedia, http:\/\/en.wikipedia.org\/"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Freedman, D.: Statistical Models: Theory and Practice. Cambridge University Press, New York (2005)","DOI":"10.1017\/CBO9781139165495"},{"key":"2_CR18","first-page":"391","volume-title":"Proc. of the Third Joint BCS and ACM Symposium on Research and Development in Information Retrieval","author":"N. Fuhr","year":"1984","unstructured":"Fuhr, N., Knorz, G.E.: Retrieval test evaluation of a rule based automatic indexing (air\/phys). In: Proc. of the Third Joint BCS and ACM Symposium on Research and Development in Information Retrieval, pp. 391\u2013408. Cambridge University Press, Cambridge (1984)"},{"key":"2_CR19","first-page":"1606","volume-title":"Proceedings of the 20th International Joint Conference on Artifical Intelligence","author":"E. Gabrilovich","year":"2007","unstructured":"Gabrilovich, E., Markovitch, S.: Computing semantic relatedness using wikipedia-based explicit semantic analysis. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, pp. 1606\u20131611. Morgan Kaufmann Publishers Inc, San Francisco (2007)"},{"issue":"1","key":"2_CR20","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M. Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The weka data mining software: an update. SIGKDD Explor. Newsl.\u00a011(1), 10\u201318 (2009)","journal-title":"SIGKDD Explor. Newsl."},{"key":"2_CR21","series-title":"NIPS 1997","first-page":"507","volume-title":"Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems 10","author":"T. Hastie","year":"1997","unstructured":"Hastie, T., Tibshirani, R.: Classification by pairwise coupling. In: Proceedings of the 1997 Conference on Advances in Neural Information Processing Systems 10. NIPS 1997, pp. 507\u2013513. MIT Press, Cambridge (1997)"},{"key":"2_CR22","first-page":"49","volume-title":"IAAI 1990: Proceedings of the The Second Conference on Innovative Applications of Artificial Intelligence","author":"P.J. Hayes","year":"1991","unstructured":"Hayes, P.J., Weinstein, S.P.: Construe\/tis: A system for content-based indexing of a database of news stories. In: IAAI 1990: Proceedings of the The Second Conference on Innovative Applications of Artificial Intelligence, pp. 49\u201364. AAAI Press, Menlo Park (1991)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Hearst, M.: Teaching applied natural language processing: triumphs and tribulations. In: TeachNLP 2005: Proceedings of the Second ACL Workshop on Effective Tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics. Association for Computational Linguistics, Morristown, NJ, USA (2005)","DOI":"10.3115\/1627291.1627293"},{"key":"2_CR24","unstructured":"Hitz, F.: Why Spy?: Espionage in an Age of Uncertainty. Thomas Dunne Books (2008)"},{"key":"2_CR25","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1145\/1390334.1390367","volume-title":"Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","author":"J. Hu","year":"2008","unstructured":"Hu, J., Fang, L., Cao, Y., Zeng, H.-J., Li, H., Yang, Q., Chen, Z.: Enhancing text clustering by leveraging wikipedia semantics. In: Proceedings of the 31st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. SIGIR 2008, pp. 179\u2013186. ACM, New York (2008)"},{"key":"2_CR26","unstructured":"Poneman Institute. Fourth annual us cost of data breach study (January 2009), http:\/\/www.ponemon.org\/local\/upload\/fckjail\/generalcontent\/18\/file\/2008-2009USCostofDataBreachReportFinal.pdf"},{"key":"2_CR27","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1023\/A:1007660820062","volume":"42","author":"N. Japkowicz","year":"2001","unstructured":"Japkowicz, N.: Supervised versus unsupervised binary-learning by feedforward neural networks. Machine Learning\u00a042, 97\u2013122 (2001)","journal-title":"Machine Learning"},{"key":"2_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/BFb0026683","volume-title":"Machine Learning: ECML-98","author":"T. Joachims","year":"1998","unstructured":"Joachims, T.: Text categorization with support vector machines: Learning with many relevant features. In: N\u00e9dellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol.\u00a01398, pp. 137\u2013142. Springer, Heidelberg (1998)"},{"key":"2_CR29","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-0907-3","volume-title":"Learning to Classify Text Using Support Vector Machines \u2013 Methods, Theory, and Algorithms","author":"T. Joachims","year":"2002","unstructured":"Joachims, T.: Learning to Classify Text Using Support Vector Machines \u2013 Methods, Theory, and Algorithms. Springer, Kluwer (2002)"},{"key":"2_CR30","volume-title":"Making large-scale support vector machine learning practical","author":"T. Joachims","year":"1999","unstructured":"Joachims, T.: Making large-scale support vector machine learning practical. MIT Press, Cambridge (1999)"},{"key":"2_CR31","unstructured":"Joachims, T.: Transductive inference for text classification using support vector machines. In: International Conference on Machine Learning (ICML), Bled, Slowenien, pp. 200\u2013209 (1999)"},{"key":"2_CR32","unstructured":"Koller, D., Lerner, U., Angelov, D.: A general algorithm for approximate inference and its application to hybrid bayes nets. In: Proceedings of the Fifteenth Annual Conference on Uncertainty in Artificial Intelligence (1999)"},{"key":"2_CR33","unstructured":"Lewis, D.: Reuters 21578, http:\/\/www.daviddlewis.com\/resources\/testcollections\/reuters21578\/"},{"key":"2_CR34","first-page":"587","volume-title":"IJCAI 2003: Proceedings of the 18th International Joint Conference on Artificial Intelligence","author":"X. Li","year":"2003","unstructured":"Li, X., Liu, B.: Learning to classify texts using positive and unlabeled data. In: IJCAI 2003: Proceedings of the 18th International Joint Conference on Artificial Intelligence, pp. 587\u2013592. Morgan Kaufmann Publishers Inc, San Francisco (2003)"},{"key":"2_CR35","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"C.D. Manning","year":"2008","unstructured":"Manning, C.D., Raghavan, P., Schtze, H.: Introduction to Information Retrieval. Cambridge University Press, New York (2008)"},{"issue":"3","key":"2_CR36","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1145\/321075.321084","volume":"8","author":"M.E. Maron","year":"1961","unstructured":"Maron, M.E.: Automatic indexing: An experimental inquiry. J. ACM\u00a08(3), 404\u2013417 (1961)","journal-title":"J. ACM"},{"key":"2_CR37","unstructured":"McAfee. Data loss prevention, http:\/\/www.mcafee.com\/us\/enterprise\/products\/data_loss_prevention\/"},{"key":"2_CR38","unstructured":"Transcendental Meditation. Transcendental meditation websites, http:\/\/www.alltm.org , http:\/\/www.alltm.org"},{"key":"2_CR39","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/SYNASC.2007.8","volume-title":"Proceedings of the Ninth International Symposium on Symbolic and Numeric Algorithms for Scientific Computing","author":"Z. Minier","year":"2007","unstructured":"Minier, Z., Bodo, Z., Csato, L.: Wikipedia-based kernels for text categorization. In: Proceedings of the Ninth International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, pp. 157\u2013164. IEEE Computer Society Press, Los Alamitos (2007)"},{"key":"2_CR40","first-page":"258","volume-title":"Proceedings of the Sixteenth International Conference on Machine Learning","author":"D. Mladenic","year":"1999","unstructured":"Mladenic, D., Grobelnik, M.: Feature selection for unbalanced class distribution and naive bayes. In: Proceedings of the Sixteenth International Conference on Machine Learning. ICML 1999, pp. 258\u2013267. Morgan Kaufmann, San Francisco (1999)"},{"key":"2_CR41","unstructured":"Ng, K.: A comparative study of the practical characteristics of neural network and conventional pattern classifiers. Technical report (1990)"},{"key":"2_CR42","unstructured":"Church of\u00a0Jesus Christ\u00a0of Latter Day Saints. Church of jesus christ of latter day saints website, http:\/\/lds.org"},{"key":"2_CR43","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1145\/1367497.1367510","volume-title":"Proceeding of the 17th International Conference on World Wide Web (WWW 2008)","author":"X.-H. Phan","year":"2008","unstructured":"Phan, X.-H., Nguyen, L.-M., Horiguchi, S.: Learning to classify short and sparse text & web with hidden topics from large-scale data collections. In: Proceeding of the 17th International Conference on World Wide Web (WWW 2008), pp. 91\u2013100. ACM, New York (2008)"},{"key":"2_CR44","unstructured":"Proofpoint. Outbound email security and data loss prevention, http:\/\/www.proofpoint.com\/id\/outbound\/index.php"},{"key":"2_CR45","unstructured":"proofpoint. Unified email security, email archiving, data loss prevention and encryption, http:\/\/www.proofpoint.com\/products\/"},{"key":"2_CR46","unstructured":"RSA Data Loss Prevention, http:\/\/www.rsa.com\/node.aspx?id=1130"},{"key":"2_CR47","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/3-540-46769-6_2","volume-title":"Algorithmic Learning Theory","author":"R.E. Schapire","year":"1999","unstructured":"Schapire, R.E.: Theoretical Views of Boosting and Applications. In: Watanabe, O., Yokomori, T. (eds.) ALT 1999. LNCS (LNAI), vol.\u00a01720, pp. 13\u201325. Springer, Heidelberg (1999)"},{"issue":"1","key":"2_CR48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F. Sebastiani","year":"2002","unstructured":"Sebastiani, F.: Machine learning in automated text categorization. ACM Comput. Surv.\u00a034(1), 1\u201347 (2002)","journal-title":"ACM Comput. Surv."},{"key":"2_CR49","first-page":"1419","volume-title":"Proceedings of the 21st National Conference on Artificial Intelligence","author":"M. Strube","year":"2006","unstructured":"Strube, M., Ponzetto, S.P.: Wikirelate! computing semantic relatedness using wikipedia. In: Proceedings of the 21st National Conference on Artificial Intelligence, vol.\u00a02, pp. 1419\u20131424. AAAI Press, Menlo Park (2006)"},{"key":"2_CR50","unstructured":"Symantec. Data Loss Prevention Products & Services, http:\/\/www.symantec.com\/business\/theme.jsp?themeid=vontu"},{"key":"2_CR51","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1145\/1284420.1284467","volume-title":"DocEng 2007: Proceedings of the 2007 ACM symposium on Document engineering","author":"T.T. Thet","year":"2007","unstructured":"Thet, T.T., Na, J.-C., Khoo, C.S.G.: Filtering product reviews from web search results. In: DocEng 2007: Proceedings of the 2007 ACM symposium on Document engineering, pp. 196\u2013198. ACM, New York (2007)"},{"key":"2_CR52","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/502585.502604","volume-title":"CIKM 2001: Proceedings of the Tenth International Conference on Information and Knowledge Management","author":"K. Toutanova","year":"2001","unstructured":"Toutanova, K., Chen, F., Popat, K., Hofmann, T.: Text classification in a hierarchical mixture model for small training sets. In: CIKM 2001: Proceedings of the Tenth International Conference on Information and Knowledge Management, pp. 105\u2013113. ACM, New York (2001)"},{"key":"2_CR53","unstructured":"Trend Micro. Trend Micro Data Loss Prevention, http:\/\/us.trendmicro.com\/us\/products\/enterprise\/data-loss-prevention\/"},{"key":"2_CR54","unstructured":"Trustwave. Global security report 2010 (February 2010), https:\/\/www.trustwave.com\/whitePapers.php"}],"container-title":["Lecture Notes in Computer Science","Privacy Enhancing Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-22263-4_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T03:06:57Z","timestamp":1606187217000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-22263-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011]]},"ISBN":["9783642222627","9783642222634"],"references-count":54,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-22263-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2011]]}}}