{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T07:30:21Z","timestamp":1775460621513,"version":"3.50.1"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319105536","type":"print"},{"value":"9783319105543","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10554-3_12","type":"book-chapter","created":{"date-parts":[[2014,9,4]],"date-time":"2014-09-04T18:27:59Z","timestamp":1409855279000},"page":"129-138","source":"Crossref","is-referenced-by-count":1,"title":["Training Datasets Collection and Evaluation of Feature Selection Methods for Web Content Filtering"],"prefix":"10.1007","author":[{"given":"Roman","family":"Suvorov","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilya","family":"Sochenkov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilya","family":"Tikhomirov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"12_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/978-3-319-01931-4_31","volume-title":"Speech and Computer","author":"R. Suvorov","year":"2013","unstructured":"Suvorov, R., Sochenkov, I., Tikhomirov, I.: Method for pornography filtering in the WEB based on automatic classification and natural language processing. In: \u017delezn\u00fd, M., Habernal, I., Ronzhin, A. (eds.) SPECOM 2013. LNCS, vol.\u00a08113, pp. 233\u2013240. Springer, Heidelberg (2013)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"de Groc, C.: Babouk: Focused web crawling for corpus compilation and automatic terminology extraction. In: 2011 IEEE\/WIC\/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), vol.\u00a01, pp. 497\u2013498 (August 2011)","DOI":"10.1109\/WI-IAT.2011.253"},{"issue":"1-2","key":"12_CR3","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1023\/A:1009982220290","volume":"1","author":"Y. Yang","year":"1999","unstructured":"Yang, Y.: An evaluation of statistical approaches to text categorization. Information Retrieval\u00a01(1-2), 69\u201390 (1999)","journal-title":"Information Retrieval"},{"issue":"1","key":"12_CR4","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":"12_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1007\/978-3-642-02457-3_74","volume-title":"Computational Science and Its Applications \u2013 ICCSA 2009","author":"H. Dong","year":"2009","unstructured":"Dong, H., Hussain, F.K., Chang, E.: State of the art in semantic focused crawlers. In: Gervasi, O., Taniar, D., Murgante, B., Lagan\u00e0, A., Mun, Y., Gavrilova, M.L. (eds.) ICCSA 2009, Part II. LNCS, vol.\u00a05593, pp. 910\u2013924. Springer, Heidelberg (2009)"},{"key":"12_CR6","unstructured":"Baroni, M., Bernardini, S.: Bootcat: Bootstrapping corpora and terms from the web. In: LREC (2004)"},{"key":"12_CR7","unstructured":"AOL Inc.: Open directory project, \n                    \n                      http:\/\/www.dmoz.org"},{"key":"12_CR8","doi-asserted-by":"publisher","first-page":"1109","DOI":"10.1145\/1526709.1526880","volume-title":"Proceedings of the 18th International Conference on World Wide Web, WWW 2009","author":"E. Baykan","year":"2009","unstructured":"Baykan, E., Henzinger, M., Marian, L., Weber, I.: Purely url-based topic classification. In: Proceedings of the 18th International Conference on World Wide Web, WWW 2009, pp. 1109\u20131110. ACM, New York (2009)"},{"key":"12_CR9","first-page":"193","volume-title":"Proceedings of the 13th International Conference on World Wide Web, WWW 2004","author":"L.K. Shih","year":"2004","unstructured":"Shih, L.K., Karger, D.R.: Using urls and table layout for web classification tasks. In: Proceedings of the 13th International Conference on World Wide Web, WWW 2004, pp. 193\u2013202. ACM, New York (2004)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Aggarwal, C.C., Al-Garawi, F., Yu, P.S.: Intelligent crawling on the world wide web with arbitrary predicates. In: Proceedings of the 10th International Conference on World Wide Web, pp. 96\u2013105. ACM (2001)","DOI":"10.1145\/371920.371955"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Jamali, M., Sayyadi, H., Hariri, B.B., Abolhassani, H.: A method for focused crawling using combination of link structure and content similarity. In: IEEE\/WIC\/ACM International Conference on Web Intelligence, WI 2006, pp. 753\u2013756. IEEE (2006)","DOI":"10.1109\/WI.2006.19"},{"key":"12_CR12","volume-title":"Introduction to modern information retrieval","author":"G. Salton","year":"1983","unstructured":"Salton, G., McGill, M.J.: Introduction to modern information retrieval. McGraw-Hill, New York (1983)"},{"key":"12_CR13","unstructured":"Porter, M.F.: Snowball: A language for stemming algorithms (2001)"},{"key":"12_CR14","unstructured":"Liu, T., Liu, S., Chen, Z., Ma, W.Y.: An evaluation on feature selection for text clustering. In: ICML, vol.\u00a03, pp. 488\u2013495 (2003)"},{"key":"12_CR15","unstructured":"Mitchell, T.: Machine Learning. McGraw Hill (1997)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Osipov, G., Smirnov, I., Tikhomirov, I., Vybornova, O.: Technologies for semantic analysis of scientific publications. In: 2012 6th IEEE International Conference on Intelligent Systems (IS), pp. 058\u2013062 (September 2012)","DOI":"10.1109\/IS.2012.6335191"},{"key":"12_CR17","unstructured":"Osipov, G., Smirnov, I., Tikhomirov, I., Shelmanov, A.: Relational-situational method for intelligent search and analysis of scientific publications. In: Proceedings of the Integrating IR Technologies for Professional Search Workshop, pp. 57\u201364 (2013)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence: Methodology, Systems, and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10554-3_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,27]],"date-time":"2019-05-27T15:48:01Z","timestamp":1558972081000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10554-3_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319105536","9783319105543"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10554-3_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}