{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:26:19Z","timestamp":1742948779194,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":98,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642032257"},{"type":"electronic","value":"9783642032264"}],"license":[{"start":{"date-parts":[[2009,1,1]],"date-time":"2009-01-01T00:00:00Z","timestamp":1230768000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009]]},"DOI":"10.1007\/978-3-642-03226-4_2","type":"book-chapter","created":{"date-parts":[[2009,9,14]],"date-time":"2009-09-14T10:43:15Z","timestamp":1252924995000},"page":"11-38","source":"Crossref","is-referenced-by-count":4,"title":["Text and Hypertext Categorization"],"prefix":"10.1007","author":[{"given":"Houda","family":"Benbrahim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Max","family":"Bramer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"5","key":"2_CR1","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1016\/S0306-4573(99)00012-6","volume":"35","author":"G. Amati","year":"1999","unstructured":"Amati, G., Crestani, F.: Probabilistic learning for selective dissemination of information. Information Processing and Management\u00a035(5), 633\u2013654 (1999)","journal-title":"Information Processing and Management"},{"key":"2_CR2","unstructured":"Andrews, K.: The development of a fast conflation algorithm for English. Dissertation submitted for the Diploma in Computer Science (unpublished), University of Cambridge (1971)"},{"issue":"3","key":"2_CR3","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1145\/183422.183423","volume":"12","author":"C. Apt\u00e9","year":"1994","unstructured":"Apt\u00e9, C., Damerau, F., et al.: Automated learning of decision rules for text categorization. ACM Transactions on Information Systems (TOIS)\u00a012(3), 233\u2013251 (1994)","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"2_CR4","unstructured":"Attardi, G., Gulli, A., et al.: Automatic Web Page Categorization by Link and Context Analysis. In: Proceedings of THAI\u201999, pp. 105\u2013119 (1999)"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Baker, L.D., McCallum, A.K.: Distributional clustering of words for text classification. In: Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pp. 96\u2013103 (1998)","DOI":"10.1145\/290941.290970"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Benbrahim, H., Bramer, M.: An empirical study for hypertext categorization. In: IEEE International Conference on Systems, Man and Cybernetics, 2004, vol.\u00a06 (2004a)","DOI":"10.1109\/ICSMC.2004.1401147"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Benbrahim, H., Bramer, M.: Neighbourhood Exploitation in Hypertext Categorization. In: Proceedings of the Twenty-fourth SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence, Cambridge, December 2004, pp. 258\u2013268 (2004b)","DOI":"10.1007\/1-84628-102-4_19"},{"key":"2_CR8","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/978-0-387-09695-7_10","volume-title":"Artificial Intelligence in Theory and Practice II","author":"H. Benbrahim","year":"2008","unstructured":"Benbrahim, H., Bramer, M.: A Fuzzy Semi-Supervised Support Vector Machines Approach to Hypertext Categorization. In: Artificial Intelligence in Theory and Practice II, pp. 97\u2013106. Springer, Heidelberg (2008)"},{"issue":"1-7","key":"2_CR9","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/S0169-7552(98)00127-5","volume":"30","author":"K. Bharat","year":"1998","unstructured":"Bharat, K., Broder, A.Z.: A Technique for Measuring the Relative Size and Overlap of Public Web Search Engines. WWW7 \/ Computer Networks\u00a030(1-7), 379\u2013388 (1998)","journal-title":"WWW7 \/ Computer Networks"},{"issue":"2","key":"2_CR10","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. Journal of the ACM (JACM)\u00a010(2), 151\u2013162 (1963)","journal-title":"Journal of the ACM (JACM)"},{"key":"2_CR11","volume-title":"Principles of Data Mining","author":"M.A. Bramer","year":"2007","unstructured":"Bramer, M.A.: Principles of Data Mining. Springer, Heidelberg (2007)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Buckley, C., Salton, G., et al.: Automatic query expansion using SMART. In: TREC 3, Overview of the Third Text Retrieval Conference (TREC-3), pp. 500\u2013225 (1995)","DOI":"10.6028\/NIST.SP.500-225.routing-cornell"},{"key":"2_CR13","unstructured":"Caropreso, M.F., Matwin, S., et al.: A learner-independent evaluation of the usefulness of statistical phrases for automated text categorization. In: Text Databases and Document Management: Theory and Practice, pp. 78\u2013102 (2001)"},{"key":"2_CR14","unstructured":"Cavnar, W.B., Trenkle, J.M.: N-Gram based document categorization. In: Proceedings of the Third Symposium on Document Analysis and Information Retrieval, Las Vegas, pp. 161\u2013176 (1994)"},{"key":"2_CR15","unstructured":"Chakrabarti, S., Dom, B., et al.: Using taxonomy, discriminants, and signatures for navigating in text databases. In: Proceedings of the 23rd VLDB Conference, pp. 446\u2013455 (1997)"},{"issue":"3","key":"2_CR16","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1007\/s007780050061","volume":"7","author":"S. Chakrabarti","year":"1998","unstructured":"Chakrabarti, S., Dom, B., et al.: Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomies. The VLDB Journal The International Journal on Very Large Data Bases\u00a07(3), 163\u2013178 (1998)","journal-title":"The VLDB Journal The International Journal on Very Large Data Bases"},{"key":"2_CR17","unstructured":"Chakrabarti, S., Dom, B.E., et al.: Enhanced hypertext categorization using hyperlinks. Google Patents (2002)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Chen, H., Dumais, S.: Bringing order to the web: automatically categorizing search results. In: Proceedings of the SIGCHI conference on Human factors in computing systems, pp. 145\u2013152 (2000)","DOI":"10.1145\/332040.332418"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Clack, C., Farringdon, J., et al.: Autonomous document classification for business. In: Proceedings of the 1st International Conference on Autonomous Agents, pp. 201\u2013208 (1997)","DOI":"10.1145\/267658.267716"},{"key":"2_CR20","unstructured":"Cohen, W.W., Hirsh, H.: Joins that generalize: text classification using Whirl. In: Proceedings of KDD-98, 4th International Conference on Knowledge Discovery and Data Mining, pp. 169\u2013173 (1998)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Cohen, W.W., Singer, Y.: Context-Sensitive Learning Methods for Text Categorization. In: Conference on Research and Development in Information Retrieval (SIGIR), pp. 307\u2013315 (1998)","DOI":"10.1145\/243199.243278"},{"key":"2_CR22","unstructured":"Creecy, R.H.: Trading MIPS and Memory for Knowledge Engineering: Automatic Classification of Census Returns on a Massively Parallel Supercomputer. Thinking Machines Corp. (1991)"},{"key":"2_CR23","unstructured":"Dagan, I., Karov, Y., et al.: Mistake-driven learning in text categorization. In: Proceedings of the Second Conference on Empirical Methods in NLP, pp. 55\u201363 (1997)"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Dattola, R.T.: FIRST: Flexible Information Retrieval System for Text. J. Am. Soc. Inf. Sci.\u00a030(1) (1979)","DOI":"10.1002\/asi.4630300103"},{"issue":"5","key":"2_CR25","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/0306-4573(82)90001-2","volume":"18","author":"T. Heer De","year":"1982","unstructured":"De Heer, T.: The application of the concept of homeosemy to natural language information retrieval. Information Processing & Management\u00a018(5), 229\u2013236 (1982)","journal-title":"Information Processing & Management"},{"issue":"6","key":"2_CR26","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9","volume":"41","author":"S. Deerwester","year":"1990","unstructured":"Deerwester, S., Dumais, S.T., et al.: Indexing by latent semantic analysis. Journal of the American Society for Information Science\u00a041(6), 391\u2013407 (1990)","journal-title":"Journal of the American Society for Information Science"},{"issue":"2","key":"2_CR27","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1023\/A:1007413511361","volume":"29","author":"P. Domingos","year":"1997","unstructured":"Domingos, P., Pazzani, M.: On the Optimality of the Simple Bayesian Classifier under Zero-One Loss. Machine Learning\u00a029(2), 103\u2013130 (1997)","journal-title":"Machine Learning"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Dumais, S., Platt, J., et al.: Inductive learning algorithms and representations for text categorization. In: Proceedings of the seventh international conference on Information and knowledge management, pp. 148\u2013155 (1998)","DOI":"10.1145\/288627.288651"},{"issue":"2","key":"2_CR29","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3758\/BF03203370","volume":"23","author":"S.T. Dumais","year":"1991","unstructured":"Dumais, S.T.: Improving the retrieval of information from external sources. Behavior Research Methods, Instruments and Computers\u00a023(2), 229\u2013236 (1991)","journal-title":"Behavior Research Methods, Instruments and Computers"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Escudero, G., Marquez, L., et al.: Boosting Applied to Word Sense Disambiguation. Arxiv preprint cs.CL\/0007010 (2000)","DOI":"10.1007\/3-540-45164-1_14"},{"issue":"4","key":"2_CR31","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1108\/eb026605","volume":"31","author":"B. Field","year":"1975","unstructured":"Field, B.: Towards automatic indexing: automatic assignment of controlled-language indexing and classification from free indexing. Journal of Documentation\u00a031(4), 246\u2013265 (1975)","journal-title":"Journal of Documentation"},{"issue":"3","key":"2_CR32","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1145\/125187.125189","volume":"9","author":"N. Fuhr","year":"1991","unstructured":"Fuhr, N., Buckley, C.: A probabilistic learning approach for document indexing. ACM Transactions on Information Systems (TOIS)\u00a09(3), 223\u2013248 (1991)","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"2_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/3-540-48412-4_41","volume-title":"Advances in Intelligent Data Analysis","author":"J. Furnkranz","year":"1999","unstructured":"Furnkranz, J.: Exploiting structural information for text classification on the WWW. In: Hand, D.J., Kok, J.N., R. Berthold, M. (eds.) IDA 1999. LNCS, vol.\u00a01642, pp. 487\u2013497. Springer, Heidelberg (1999)"},{"key":"2_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/3-540-45268-0_6","volume-title":"Research and Advanced Technology for Digital Libraries","author":"L. Galavotti","year":"2000","unstructured":"Galavotti, L., Sebastiani, F., Simi, M.: Experiments on the use of feature selection and negative evidence in automated text categorization. In: Borbinha, J.L., Baker, T. (eds.) ECDL 2000. LNCS, vol.\u00a01923, pp. 59\u201368. Springer, Heidelberg (2000)"},{"issue":"5","key":"2_CR35","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/BF00136984","volume":"26","author":"W.A. Gale","year":"1992","unstructured":"Gale, W.A., Church, K.W., et al.: A method for disambiguating word senses in a large corpus. Computers and the Humanities\u00a026(5), 415\u2013439 (1992)","journal-title":"Computers and the Humanities"},{"issue":"4","key":"2_CR36","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/0020-0271(71)90002-7","volume":"7","author":"W.A. Gray","year":"1971","unstructured":"Gray, W.A., Harley, A.J.: Computer-assisted indexing. Inform. Storage Retrieval\u00a07(4), 167\u2013174 (1971)","journal-title":"Inform. Storage Retrieval"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Hersh, W., Buckley, C., et al.: OHSUMED: An interactive retrieval evaluation and new large test collection for research. In: Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 192\u2013201 (1994)","DOI":"10.1007\/978-1-4471-2099-5_20"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Hull, D.: Improving text retrieval for the routing problem using latent semantic indexing. In: Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 282\u2013291 (1994)","DOI":"10.1007\/978-1-4471-2099-5_29"},{"key":"2_CR39","unstructured":"Ittner, D.J., Lewis, D.D., et al.: Text categorization of low quality images. In: Symposium on Document Analysis and Information Retrieval, pp. 301\u2013315 (1995)"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Iyer, R.D., Lewis, D.D., et al.: Boosting for document routing. In: Proceedings of the ninth international conference on Information and knowledge management, pp. 70\u201377 (2000)","DOI":"10.1145\/354756.354794"},{"key":"2_CR41","unstructured":"Joachims, T.: A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization, School of Computer Science, Carnegie Mellon University (1996)"},{"key":"2_CR42","volume-title":"Text Categorization with Suport Vector Machines: Learning with Many Relevant Features","author":"T. Joachims","year":"1998","unstructured":"Joachims, T.: Text Categorization with Suport Vector Machines: Learning with Many Relevant Features. Springer, London (1998)"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Kim, Y.H., Hahn, S.Y., et al.: Text filtering by boosting naive Bayes classifiers. In: Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, pp. 168\u2013175 (2000)","DOI":"10.1145\/345508.345572"},{"key":"2_CR44","unstructured":"Koller, D., Sahami, M.: Hierarchically classifying documents using very few words. In: Proceedings of the Fourteenth International Conference on Machine Learning, pp. 170\u2013178 (1997)"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Lam, S.L.Y., Lee, D.L.: Feature reduction for neural network based text categorization. In: Proceedings of 6th International Conference on Database Systems for Advanced Applications, pp. 195\u2013202 (1999)","DOI":"10.1109\/DASFAA.1999.765752"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Lam, W., Ho, C.Y.: Using a generalized instance set for automatic text categorization. In: Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pp. 81\u201389 (1998)","DOI":"10.1145\/290941.290961"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Lang, K.: Newsweeder: Learning to filter netnews. In: Proceedings of the Twelfth International Conference on Machine Learning, pp. 331\u2013339 (1995)","DOI":"10.1016\/B978-1-55860-377-6.50048-7"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Larkey, L.S.: Automatic essay grading using text categorization techniques. In: Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval, pp. 90\u201395 (1998)","DOI":"10.1145\/290941.290965"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Larkey, L.S.: A patent search and classification system. In: Proceedings of the fourth ACM conference on Digital libraries, pp. 179\u2013187 (1999)","DOI":"10.1145\/313238.313304"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Larkey, L.S., Croft, W.B.: Combining classifiers in text categorization. In: Proceedings of the 19th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 289\u2013297 (1996)","DOI":"10.1145\/243199.243276"},{"key":"2_CR51","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1038\/21987","volume":"400","author":"S. Lawrence","year":"1999","unstructured":"Lawrence, S., Giles, C.L.: Accessibility of information on the web. Nature\u00a0400, 107 (1999)","journal-title":"Nature"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Lewis, D.D.: An evaluation of phrasal and clustered representations on a text categorization task. In: Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 37\u201350 (1992)","DOI":"10.1145\/133160.133172"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Lewis, D.D.: Feature selection and feature extraction for text categorization. In: Proceedings of the workshop on Speech and Natural Language, pp. 212\u2013217 (1992)","DOI":"10.3115\/1075527.1075574"},{"key":"2_CR54","unstructured":"Lewis, D.D.: Representation and learning in information retrieval. PhD Thesis, Department of Computer and Information Science, University of Massachusetts (1992)"},{"key":"2_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/BFb0026666","volume-title":"Machine Learning: ECML-98","author":"D.D. Lewis","year":"1998","unstructured":"Lewis, D.D.: Naive (Bayes) at forty: The independence assumption in information retrieval. In: N\u00e9dellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol.\u00a01398, pp. 4\u201315. Springer, Heidelberg (1998)"},{"key":"2_CR56","unstructured":"Lewis, D.D., Ringuette, M.: A comparison of two learning algorithms for text categorization. In: Third Annual Symposium on Document Analysis and Information Retrieval, pp. 81\u201393 (1994)"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Li, H., Yamanishi, K.: Text classification using ESC-based stochastic decision lists. In: Proceedings of the eighth international conference on Information and knowledge management, pp. 122\u2013130 (1999)","DOI":"10.1145\/319950.319966"},{"issue":"8","key":"2_CR58","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1093\/comjnl\/41.8.537","volume":"41","author":"Y.H. Li","year":"1998","unstructured":"Li, Y.H., Jain, A.K.: Classification of Text Documents. The Computer Journal\u00a041(8), 537 (1998)","journal-title":"The Computer Journal"},{"key":"2_CR59","unstructured":"Lovins, J.B.: Development of a Stemming Algorithm. MIT Information Processing Group, Electronic Systems Laboratory (1968)"},{"issue":"2","key":"2_CR60","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1147\/rd.22.0159","volume":"2","author":"H.P. Luhn","year":"1958","unstructured":"Luhn, H.P.: The automatic creation of literature abstracts. IBM Journal of Research and Development\u00a02(2), 159\u2013165 (1958)","journal-title":"IBM Journal of Research and Development"},{"key":"2_CR61","volume-title":"Foundations of Statistical Natural Language Processing","author":"C.D. Manning","year":"1999","unstructured":"Manning, C.D., Sch\u00fctze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)"},{"key":"2_CR62","unstructured":"Masand, B.: Optimizing confidence of text classification by evolution of symbolic expressions. Mit Press In Series In Complex Adaptive Systems, pp. 445\u2013458 (1994)"},{"key":"2_CR63","doi-asserted-by":"crossref","unstructured":"Masand, B., Linoff, G., et al.: Classifying news stories using memory based reasoning. In: Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 59\u201365 (1992)","DOI":"10.1145\/133160.133177"},{"key":"2_CR64","unstructured":"McCallum, A., Nigam, K.: Employing EM in pool-based active learning for text classification. In: Proceedings of ICML-98, 15th International Conference on Machine Learning, pp. 350\u2013358 (1998)"},{"key":"2_CR65","volume-title":"Introduction to modern information retrieval","author":"M.J. McGill","year":"1983","unstructured":"McGill, M.J., Salton, G.: Introduction to modern information retrieval. McGraw-Hill, New York (1983)"},{"key":"2_CR66","volume-title":"WordNet","author":"G. Miller","year":"1998","unstructured":"Miller, G., Princeton, U., et al.: WordNet. MIT Press, Cambridge (1998)"},{"key":"2_CR67","unstructured":"Mladenic, D., Grobelnik, M.: Word sequences as features in text-learning. In: Proceedings of ERK-98, the Seventh Electrotechnical and Computer Science Conference, pp. 145\u2013148 (1998)"},{"key":"2_CR68","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/3-540-60925-3_58","volume-title":"Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing","author":"I. Moulinier","year":"1996","unstructured":"Moulinier, I., Ganascia, J.G.: Applying an existing machine learning algorithm to text categorization. In: Wermter, S., Scheler, G., Riloff, E. (eds.) IJCAI-WS 1995. LNCS, vol.\u00a01040, pp. 343\u2013354. Springer, Heidelberg (1996)"},{"key":"2_CR69","unstructured":"Moulinier, I., Raskinis, G., et al.: Text categorization: a symbolic approach. In: Proceedings of the Fifth Annual Symposium on Document Analysis and Information Retrieval (1996)"},{"key":"2_CR70","doi-asserted-by":"crossref","unstructured":"Ng, H.T., Goh, W.B., et al.: Feature selection, perception learning, and a usability case study for text categorization. In: Proceedings of the 20th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 67\u201373 (1997)","DOI":"10.1145\/258525.258537"},{"key":"2_CR71","doi-asserted-by":"crossref","unstructured":"Nigam, K., Ghani, R.: Analyzing the effectiveness and applicability of co-training. In: Proceedings of the ninth international conference on Information and knowledge management, pp. 86\u201393 (2000)","DOI":"10.1145\/354756.354805"},{"key":"2_CR72","doi-asserted-by":"crossref","unstructured":"Oh, H.J., Myaeng, S.H., et al.: A practical hypertext catergorization method using links and incrementally available class information. In: Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval, pp. 264\u2013271 (2000)","DOI":"10.1145\/345508.345594"},{"key":"2_CR73","first-page":"277","volume":"6","author":"A.E. Petrarca","year":"1969","unstructured":"Petrarca, A.E., Lay, W.M.: Use of an automatically generated authority list to eliminate scattering caused by some singular and plural main index terms. Proceedings of the American Society for Information Science\u00a06, 277\u2013282 (1969)","journal-title":"Proceedings of the American Society for Information Science"},{"key":"2_CR74","unstructured":"Pierre, J.M.: Practical Issues for Automated Categorization of Web Sites. In: Electronic Proc. ECDL 2000 Workshop on Semantic Web (2000)"},{"issue":"3","key":"2_CR75","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"M. Porter","year":"1980","unstructured":"Porter, M.: An Algorithm for Suffix Stripping Program. Program\u00a014(3), 130\u2013137 (1980)","journal-title":"Program"},{"issue":"1","key":"2_CR76","first-page":"81","volume":"1","author":"J.R. Quinlan","year":"1986","unstructured":"Quinlan, J.R.: Induction of decision trees. Machine Learning\u00a01(1), 81\u2013106 (1986)","journal-title":"Machine Learning"},{"key":"2_CR77","doi-asserted-by":"crossref","unstructured":"Ruiz, M.E., Srinivasan, P.: Hierarchical neural networks for text categorization (poster abstract). In: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, pp. 281\u2013282 (1999)","DOI":"10.1145\/312624.312700"},{"issue":"3","key":"2_CR78","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1007\/s007990000038","volume":"3","author":"C.L. Sable","year":"2000","unstructured":"Sable, C.L., Hatzivassiloglou, V.: Text-based approaches for non-topical image categorization. International Journal on Digital Libraries\u00a03(3), 261\u2013275 (2000)","journal-title":"International Journal on Digital Libraries"},{"issue":"5","key":"2_CR79","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","volume":"24","author":"G. Salton","year":"1988","unstructured":"Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Information Processing and Management\u00a024(5), 513\u2013523 (1988)","journal-title":"Information Processing and Management"},{"issue":"11","key":"2_CR80","doi-asserted-by":"publisher","first-page":"613","DOI":"10.1145\/361219.361220","volume":"18","author":"G. Salton","year":"1975","unstructured":"Salton, G., Wong, A., et al.: A vector space model for information retrieval. Communications of the ACM\u00a018(11), 613\u2013620 (1975)","journal-title":"Communications of the ACM"},{"issue":"2","key":"2_CR81","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1023\/A:1007649029923","volume":"39","author":"R.E. Schapire","year":"2000","unstructured":"Schapire, R.E., Singer, Y.: BoosTexter: A Boosting-based System for Text Categorization. Machine Learning\u00a039(2), 135\u2013168 (2000)","journal-title":"Machine Learning"},{"key":"2_CR82","doi-asserted-by":"crossref","unstructured":"Sch\u00fctze, H., Hull, D.A., et al.: A comparison of classifiers and document representations for the routing problem. In: Proceedings of the 18th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 229\u2013237 (1995)","DOI":"10.1145\/215206.215365"},{"key":"2_CR83","doi-asserted-by":"crossref","unstructured":"Sebastiani, F., Sperduti, A., et al.: An improved boosting algorithm and its application to automated text categorization (2000)","DOI":"10.1145\/354756.354804"},{"key":"2_CR84","first-page":"881","volume":"87","author":"M.P. Sinka","year":"2002","unstructured":"Sinka, M.P., Corne, D.W.: A large benchmark dataset for web document clustering. Soft Computing Systems: Design, Management and Applications\u00a087, 881\u2013890 (2002)","journal-title":"Soft Computing Systems: Design, Management and Applications"},{"key":"2_CR85","first-page":"48","volume":"35","author":"C. Sj","year":"1992","unstructured":"Sj, C., Waltz, D.J.: Trading mips and memory for knowledge engeneering. Communications of the ACM\u00a035, 48\u201364 (1992)","journal-title":"Communications of the ACM"},{"key":"2_CR86","unstructured":"Slattery, S., Mitchell, T.: Discovering test set regularities in relational domains. In: Proc. ICML (2000)"},{"key":"2_CR87","unstructured":"Slonim, N., Tishby, N.: The power of word clusters for text classification. In: Proceedings of ECIR-01, 23rd European Colloquium on Information Retrieval Research (2001)"},{"key":"2_CR88","unstructured":"Taira, H., Haruno, M.: Feature selection in SVM text categorization. In: Proceedings of the sixteenth national conference on Artificial intelligence and the eleventh Innovative applications of artificial intelligence conference innovative applications of artificial intelligence table of contents, pp. 480\u2013486 (1999)"},{"issue":"2-4","key":"2_CR89","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1016\/S0020-0255(99)00123-1","volume":"122","author":"D.R. Tauritz","year":"2000","unstructured":"Tauritz, D.R., Kok, J.N., et al.: Adaptive Information Filtering using evolutionary computation. Information Sciences\u00a0122(2-4), 121\u2013140 (2000)","journal-title":"Information Sciences"},{"key":"2_CR90","doi-asserted-by":"crossref","unstructured":"Tzeras, K., Hartmann, S.: Automatic indexing based on Bayesian inference networks. In: Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 22\u201335 (1993)","DOI":"10.1145\/160688.160691"},{"key":"2_CR91","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The Nature of Statistical Learning Theory","author":"V.N. Vapnik","year":"1995","unstructured":"Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, New York (1995)"},{"key":"2_CR92","unstructured":"Wai, L.A.M., Fan, L.: Using a Bayesian Network Induction Approach for Text Categorization. In: Proceedings of the 15th International Joint Conference on Artificial Intelligence, pp. 745\u2013750 (1997)"},{"issue":"4","key":"2_CR93","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1109\/5254.784086","volume":"14","author":"S.M. Weiss","year":"1999","unstructured":"Weiss, S.M., Apte, C., et al.: Maximizing text-mining performance. IEEE Intelligent Systems\u00a014(4), 63\u201369 (1999)","journal-title":"IEEE Intelligent Systems"},{"key":"2_CR94","unstructured":"Wiener, E., Pedersen, J.O., et al.: A neural network approach to topic spotting. In: Proceedings of the Fourth Annual Symposium on Document Analysis and Information Retrieval (SDAIR\u201995), pp. 317\u2013332 (1995)"},{"issue":"3","key":"2_CR95","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1145\/183422.183424","volume":"12","author":"Y. Yang","year":"1994","unstructured":"Yang, Y., Chute, C.G.: An example-based mapping method for text categorization and retrieval. ACM Transactions on Information Systems (TOIS)\u00a012(3), 252\u2013277 (1994)","journal-title":"ACM Transactions on Information Systems (TOIS)"},{"key":"2_CR96","doi-asserted-by":"crossref","unstructured":"Yang, Y., Liu, X.: A re-examination of text categorization methods. In: Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, pp. 42\u201349 (1999)","DOI":"10.1145\/312624.312647"},{"key":"2_CR97","unstructured":"Yang, Y., Pedersen, J.O.: A comparative study on feature selection in text categorization. In: Proceedings of the Fourteenth International Conference on Machine Learning 97 (1997)"},{"issue":"2","key":"2_CR98","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1023\/A:1013685612819","volume":"18","author":"Y. Yang","year":"2002","unstructured":"Yang, Y., Slattery, S., et al.: A Study of Approaches to Hypertext Categorization. Journal of Intelligent Information Systems\u00a018(2), 219\u2013241 (2002)","journal-title":"Journal of Intelligent Information Systems"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence An International Perspective"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-03226-4_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T03:55:50Z","timestamp":1739332550000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-03226-4_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009]]},"ISBN":["9783642032257","9783642032264"],"references-count":98,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-03226-4_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2009]]}}}