{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T01:24:32Z","timestamp":1744161872941},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319771151"},{"type":"electronic","value":"9783319771168"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-77116-8_44","type":"book-chapter","created":{"date-parts":[[2018,10,9]],"date-time":"2018-10-09T03:56:00Z","timestamp":1539057360000},"page":"585-601","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Approximating Multi-class Text Classification Via Automatic Generation of Training Examples"],"prefix":"10.1007","author":[{"given":"Filippo","family":"Geraci","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tiziano","family":"Papini","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,10,10]]},"reference":[{"issue":"3","key":"44_CR1","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.datak.2004.11.003","volume":"54","author":"G Adami","year":"2005","unstructured":"Adami, G., Avesani, P., Sona, D.: Clustering documents into a web directory for bootstrapping a supervised classification. Data Knowl. Eng. 54(3), 301\u2013325 (2005). https:\/\/doi.org\/10.1016\/j.datak.2004.11.003","journal-title":"Data Knowl. Eng."},{"key":"44_CR2","doi-asserted-by":"crossref","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, pp. 1109\u20131110. ACM (2009)","DOI":"10.1145\/1526709.1526880"},{"issue":"3","key":"44_CR3","doi-asserted-by":"publisher","first-page":"15:1","DOI":"10.1145\/1993053.1993057","volume":"5","author":"E Baykan","year":"2011","unstructured":"Baykan, E., Henzinger, M., Marian, L., Weber, I.: A comprehensive study of features and algorithms for URL-based topic classification. ACM Trans. Web 5(3), 15:1\u201315:29 (2011). https:\/\/doi.org\/10.1145\/1993053.1993057","journal-title":"ACM Trans. Web"},{"issue":"1","key":"44_CR4","doi-asserted-by":"publisher","first-page":"3:1","DOI":"10.1145\/2435215.2435218","volume":"7","author":"E Baykan","year":"2013","unstructured":"Baykan, E., Henzinger, M., Weber, I.: A comprehensive study of techniques for URL-based web page language classification. ACM Trans. Web 7(1), 3:1\u20133:37 (2013). https:\/\/doi.org\/10.1145\/2435215.2435218","journal-title":"ACM Trans. Web"},{"key":"44_CR5","unstructured":"Bennett, G., Scholer, F., Uitdenbogerd, A.: A comparative study of probabilistic and language models for information retrieval. In: Proceedings of the Nineteenth Conference on Australasian Database, vol. 75, pp. 65\u201374. Australian Computer Society Inc. (2008)"},{"issue":"5","key":"44_CR6","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1080\/1369118X.2012.678878","volume":"15","author":"D Boyd","year":"2012","unstructured":"Boyd, D., Crawford, K.: Critical questions for big data: provocations for a cultural, technological, and scholarly phenomenon. Inf. Commun. Soc. 15(5), 662\u2013679 (2012)","journal-title":"Inf. Commun. Soc."},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Breunig, M.M., Kriegel, H.P., Ng, R.T., Sander, J.: LOF: identifying density-based local outliers. In: ACM Sigmod Record, vol. 29, pp. 93\u2013104. ACM (2000)","DOI":"10.1145\/335191.335388"},{"key":"44_CR8","doi-asserted-by":"publisher","unstructured":"Broder, A.Z., Ciccolo, P., Fontoura, M., Gabrilovich, E., Josifovski, V., Riedel, L.: Search advertising using web relevance feedback. In: Proceedings of the 17th ACM Conference on Information and Knowledge Management, CIKM 2008, pp. 1013\u20131022. ACM, New York (2008). https:\/\/doi.org\/10.1145\/1458082.1458217","DOI":"10.1145\/1458082.1458217"},{"issue":"3","key":"44_CR9","doi-asserted-by":"publisher","first-page":"17:1","DOI":"10.1145\/1541880.1541884","volume":"41","author":"C Carpineto","year":"2009","unstructured":"Carpineto, C., Osi\u0144ski, S., Romano, G., Weiss, D.: A survey of web clustering engines. ACM Comput. Surv. 41(3), 17:1\u201317:38 (2009)","journal-title":"ACM Comput. Surv."},{"issue":"3","key":"44_CR10","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1007\/s10796-013-9435-8","volume":"15","author":"M Castellanos","year":"2013","unstructured":"Castellanos, M., Daniel, F., Garrig\u00f3s, I., Maz\u00f3n, J.N.: Business intelligence and the web. Inf. Syst. Front. 15(3), 307\u2013309 (2013)","journal-title":"Inf. Syst. Front."},{"key":"44_CR11","doi-asserted-by":"crossref","unstructured":"Charikar, M.S.: Similarity estimation techniques from rounding algorithms. In: Proceedings of STOC-02, 34th Annual ACM Symposium on the Theory of Computing, , Montreal, CA, pp. 380\u2013388 (2002)","DOI":"10.1145\/509907.509965"},{"issue":"6","key":"44_CR12","doi-asserted-by":"publisher","first-page":"2106","DOI":"10.1109\/TIE.2010.2050754","volume":"58","author":"H Dong","year":"2011","unstructured":"Dong, H., Hussain, F.: Focused crawling for automatic service discovery, annotation, and classification in industrial digital ecosystems. IEEE Trans. Ind. Electron. 58(6), 2106\u20132116 (2011)","journal-title":"IEEE Trans. Ind. Electron."},{"key":"44_CR13","doi-asserted-by":"publisher","unstructured":"Eickhoff, C., Serdyukov, P., de Vries, A.P.: Web page classification on child suitability. In: Proceedings of the 19th ACM International Conference on Information and Knowledge Management, CIKM 2010, pp. 1425\u20131428. ACM, New York (2010). https:\/\/doi.org\/10.1145\/1871437.1871638","DOI":"10.1145\/1871437.1871638"},{"key":"44_CR14","doi-asserted-by":"publisher","unstructured":"Erd\u00e9lyi, M., Garz\u00f3, A., Bencz\u00far, A.A.: Web spam classification: a few features worth more. In: Proceedings of the 2011 Joint WICOW\/AIRWeb Workshop on Web Quality, WebQuality 2011, pp. 27\u201334. ACM, New York (2011). https:\/\/doi.org\/10.1145\/1964114.1964121","DOI":"10.1145\/1964114.1964121"},{"issue":"2","key":"44_CR15","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/s10618-008-0097-y","volume":"17","author":"G Forman","year":"2008","unstructured":"Forman, G.: Quantifying counts and costs via classification. Data Min. Knowl. Discov. 17(2), 164\u2013206 (2008)","journal-title":"Data Min. Knowl. Discov."},{"key":"44_CR16","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 F\u00fcrnkranz","year":"1999","unstructured":"F\u00fcrnkranz, J.: Exploiting structural information for text classification on the WWW. In: Hand, D.J., Kok, J.N., Berthold, M.R. (eds.) IDA 1999. LNCS, vol. 1642, pp. 487\u2013497. Springer, Heidelberg (1999). https:\/\/doi.org\/10.1007\/3-540-48412-4_41"},{"key":"44_CR17","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. 1, pp. 497\u2013498 (2011)","DOI":"10.1109\/WI-IAT.2011.253"},{"key":"44_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/978-3-642-28537-0_22","volume-title":"Passive and Active Measurement","author":"T Halvorson","year":"2012","unstructured":"Halvorson, T., et al.: The BIZ top-level domain: ten years later. In: Taft, N., Ricciato, F. (eds.) PAM 2012. LNCS, vol. 7192, pp. 221\u2013230. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-28537-0_22"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Hao, H.W., Mu, C.X., Yin, X.C., Li, S., Wang, Z.B.: An improved topic relevance algorithm for focused crawling. In: 2011 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 850\u2013855, October 2011","DOI":"10.1109\/ICSMC.2011.6083759"},{"key":"44_CR20","doi-asserted-by":"publisher","unstructured":"Hern\u00e1ndez, I., Rivero, C.R., Ruiz, D., Corchuelo, R.: A statistical approach to URL-based web page clustering. In: Proceedings of the 21st International Conference Companion on World Wide Web, WWW 2012 Companion, pp. 525\u2013526. ACM, New York (2012). https:\/\/doi.org\/10.1145\/2187980.2188109","DOI":"10.1145\/2187980.2188109"},{"key":"44_CR21","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.knosys.2013.12.019","volume":"57","author":"I Hern\u00e1ndez","year":"2014","unstructured":"Hern\u00e1ndez, I., Rivero, C.R., Ruiz, D., Corchuelo, R.: CALA: an unsupervised URL-based web page classification system. Knowl.-Based Syst. 57, 168\u2013180 (2014). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705113003997","journal-title":"Knowl.-Based Syst."},{"key":"44_CR22","unstructured":"Kriegel, H.P., Schubert, M.: Classification of websites as sets of feature vectors. In: Databases and Applications, pp. 127\u2013132 (2004)"},{"issue":"3","key":"44_CR23","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1561\/1500000016","volume":"3","author":"TY Liu","year":"2009","unstructured":"Liu, T.Y.: Learning to rank for information retrieval. Found. Trends Inf. Retr. 3(3), 225\u2013331 (2009). https:\/\/doi.org\/10.1561\/1500000016","journal-title":"Found. Trends Inf. Retr."},{"key":"44_CR24","unstructured":"Liu, T.Y., Xu, J., Qin, T., Xiong, W., Li, H.: LETOR: Benchmark dataset for research on learning to rank for information retrieval. In: Proceedings of SIGIR 2007 Workshop on Learning to Rank for Information Retrieval, pp. 3\u201310 (2007)"},{"issue":"4","key":"44_CR25","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1007\/s11633-012-0665-x","volume":"9","author":"JA Mangai","year":"2012","unstructured":"Mangai, J.A., Kumar, V.S., Alias Balamurugan, S.A.: A novel feature selection framework for automatic web page classification. Int. J. Autom. Comput. 9(4), 442\u2013448 (2012)","journal-title":"Int. J. Autom. Comput."},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Marath, S.T., Shepherd, M., Milios, E., Duffy, J.: Large-scale web page classification. In: 2014 47th Hawaii International Conference on System Sciences (HICSS), pp. 1813\u20131822. IEEE (2014)","DOI":"10.1109\/HICSS.2014.229"},{"key":"44_CR27","doi-asserted-by":"crossref","unstructured":"Milli, L., Monreale, A., Rossetti, G., Giannotti, F., Pedreschi, D., Sebastiani, F.: Quantification trees. In: 2013 IEEE 13th International Conference on Data Mining (ICDM), pp. 528\u2013536. IEEE (2013)","DOI":"10.1109\/ICDM.2013.122"},{"issue":"4","key":"44_CR28","doi-asserted-by":"publisher","first-page":"3407","DOI":"10.1016\/j.eswa.2010.08.126","volume":"38","author":"SA \u00d6zel","year":"2011","unstructured":"\u00d6zel, S.A.: A web page classification system based on a genetic algorithm using tagged-terms as features. Expert Syst. Appl. 38(4), 3407\u20133415 (2011). https:\/\/doi.org\/10.1016\/j.eswa.2010.08.126","journal-title":"Expert Syst. Appl."},{"key":"44_CR29","unstructured":"Patil, A.S., Pawar, B.: Automated classification of web sites using naive Bayesian algorithm. In: Proceedings of the International Multi-Conference of Engineers and Computer Scientists, vol. 1, pp. 14\u201316 (2012)"},{"issue":"2","key":"44_CR30","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1145\/1459352.1459357","volume":"41","author":"X Qi","year":"2009","unstructured":"Qi, X., Davison, B.D.: Web page classification: features and algorithms. ACM Comput. Surv. (CSUR) 41(2), 12 (2009)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"44_CR31","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/978-3-642-20573-6_55","volume-title":"Information Technology and Mobile Communication","author":"R. Rajalakshmi","year":"2011","unstructured":"Rajalakshmi, R., Aravindan, C.: Naive Bayes approach for website classification. In: Das, V.V., Thomas, G., Lumban Gaol, F. (eds.) AIM 2011. CCIS, vol. 147, pp. 323\u2013326. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-20573-6_55"},{"issue":"1","key":"44_CR32","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1108\/EUM0000000007186","volume":"53","author":"SE Robertson","year":"1997","unstructured":"Robertson, S.E.: Overview of the okapi projects. J. Doc. 53(1), 3\u20137 (1997)","journal-title":"J. Doc."},{"key":"44_CR33","doi-asserted-by":"crossref","unstructured":"Rose, D.E., Levinson, D.: Understanding user goals in web search. In: Proceedings of the 13th International Conference on World Wide Web, pp. 13\u201319. ACM (2004)","DOI":"10.1145\/988672.988675"},{"key":"44_CR34","unstructured":"Saad, M.K., Hewahi, N.M.: A comparative study of outlier mining and class outlier mining. Comput. Sci. Lett. 1(1) (2009)"},{"key":"44_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1007\/978-3-319-06028-6_104","volume-title":"Advances in Information Retrieval","author":"F Sebastiani","year":"2014","unstructured":"Sebastiani, F.: Text quantification. In: de Rijke, M. (ed.) ECIR 2014. LNCS, vol. 8416, pp. 819\u2013822. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-06028-6_104"},{"key":"44_CR36","doi-asserted-by":"crossref","unstructured":"Smith, M., Martinez, T.: Improving classification accuracy by identifying and removing instances that should be misclassified. In: The 2011 International Joint Conference on Neural Networks (IJCNN), pp. 2690\u20132697, July 2011","DOI":"10.1109\/IJCNN.2011.6033571"},{"key":"44_CR37","doi-asserted-by":"crossref","unstructured":"Tang, L., Gao, H., Liu, H.: Network quantification despite biased labels. In: Proceedings of the Eighth Workshop on Mining and Learning with Graphs, pp. 147\u2013154. ACM (2010)","DOI":"10.1145\/1830252.1830271"},{"key":"44_CR38","doi-asserted-by":"crossref","unstructured":"Taylan, D., Poyraz, M., Akyokus, S., Ganiz, M.: Intelligent focused crawler: learning which links to crawl. In: 2011 International Symposium on Innovations in Intelligent Systems and Applications (INISTA), pp. 504\u2013508, June 2011","DOI":"10.1109\/INISTA.2011.5946150"},{"issue":"4","key":"44_CR39","first-page":"67","volume":"3","author":"A Trivedi","year":"2012","unstructured":"Trivedi, A., Rai, P., Daum\u00e9 III, H., DuVall, S.L.: Leveraging social bookmarks from partially tagged corpus for improved web page clustering. ACM Trans. Intell. Syst. Technol. (TIST) 3(4), 67 (2012)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"key":"44_CR40","doi-asserted-by":"crossref","unstructured":"Wilkinson, R., Zobel, J., Sacks-davis, R.: Similarity measures for short queries. In: Fourth text Retrieval Conference (TREC-4), pp. 277\u2013285 (1995)","DOI":"10.6028\/NIST.SP.500-236.adhoc-citri"},{"key":"44_CR41","doi-asserted-by":"crossref","unstructured":"Xu, Z., Yan, F., Qin, J., Zhu, H.: A web page classification algorithm based on link information. In: 2011 Tenth International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES), pp. 82\u201386, October 2011","DOI":"10.1109\/DCABES.2011.19"},{"issue":"1","key":"44_CR42","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TKDE.2004.1264816","volume":"16","author":"H Yu","year":"2004","unstructured":"Yu, H., Han, J., Chang, K.C.: PEBL: web page classification without negative examples. IEEE Trans. Knowl. Data Eng. 16(1), 70\u201381 (2004)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"11","key":"44_CR43","first-page":"1625","volume":"6","author":"S Zhong","year":"2011","unstructured":"Zhong, S., Zou, D.: Web page classification using an ensemble of support vector machine classifiers. J. Netw. 6(11), 1625\u20131630 (2011)","journal-title":"J. Netw."}],"container-title":["Lecture Notes in Computer Science","Computational Linguistics and Intelligent Text Processing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-77116-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T04:48:03Z","timestamp":1720673283000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-77116-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319771151","9783319771168"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-77116-8_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"CICLing","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Linguistics and Intelligent Text Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Budapest","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hungary","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 April 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 April 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicling2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.cicling.org\/2017\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}