{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T04:26:54Z","timestamp":1743049614099,"version":"3.40.3"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030157180"},{"type":"electronic","value":"9783030157197"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-15719-7_1","type":"book-chapter","created":{"date-parts":[[2019,4,7]],"date-time":"2019-04-07T03:19:09Z","timestamp":1554607149000},"page":"3-11","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Open-Set Web Genre Identification Using Distributional Features and Nearest Neighbors Distance Ratio"],"prefix":"10.1007","author":[{"given":"Dimitrios","family":"Pritsos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anderson","family":"Rocha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstathios","family":"Stamatatos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,4,7]]},"reference":[{"key":"1_CR1","unstructured":"Abramson, M., Aha, D.W.: What\u2019s in a URL? Genre classification from URLs. Intelligent techniques for web personalization and recommender systems. AAAI Technical report. Association for the Advancement of Artificial Intelligence (2012)"},{"key":"1_CR2","unstructured":"Asheghi, N.R.: Human Annotation and Automatic Detection of Web Genres. Ph.D. thesis, University of Leeds (2015)"},{"key":"1_CR3","unstructured":"Asheghi, N.R., Markert, K., Sharoff, S.: Semi-supervised graph-based genre classification for web pages. In: TextGraphs-9, p. 39 (2014)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Boese, E.S., Howe, A.E.: Effects of web document evolution on genre classification. In: Proceedings of the 14th ACM International Conference on Information and Knowledge Management, pp. 632\u2013639. ACM (2005)","DOI":"10.1145\/1099554.1099715"},{"key":"1_CR5","series-title":"Text, Speech and Language Technology","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1007\/978-90-481-9178-9_4","volume-title":"Genres on the Web","author":"K Crowston","year":"2011","unstructured":"Crowston, K., Kwa\u015bnik, B., Rubleske, J.: Problems in the use-centered development of a taxonomy of web genres. In: Mehler, A., Sharoff, S., Santini, M. (eds.) Genres on the Web. Text, Speech and Language Technology, vol. 42, pp. 69\u201384. Springer, Dordrecht (2011). https:\/\/doi.org\/10.1007\/978-90-481-9178-9_4"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Dong, L., Watters, C., Duffy, J., Shepherd, M.: Binary cybergenre classification using theoretic feature measures. In: 2006 IEEE\/WIC\/ACM International Conference on Web Intelligence (WI 2006), pp. 313\u2013316 (2006)","DOI":"10.1109\/WI.2006.50"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Jebari, C.: A pure URL-based genre classification of web pages. In: 2014 25th International Workshop on Database and Expert Systems Applications (DEXA), pp. 233\u2013237. IEEE (2014)","DOI":"10.1109\/DEXA.2014.56"},{"key":"1_CR8","first-page":"13","volume":"54","author":"C Jebari","year":"2015","unstructured":"Jebari, C.: A combination based on OWA operators for multi-label genre classification of web pages. Procesamiento del Lenguaje Nat. 54, 13\u201320 (2015)","journal-title":"Procesamiento del Lenguaje Nat."},{"issue":"2","key":"1_CR9","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1145\/1041394.1041395","volume":"38","author":"H Joho","year":"2004","unstructured":"Joho, H., Sanderson, M.: The spirit collection: an overview of a large web collection. SIGIR Forum 38(2), 57\u201361 (2004)","journal-title":"SIGIR Forum"},{"issue":"5","key":"1_CR10","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1016\/j.ipm.2009.05.003","volume":"45","author":"I Kanaris","year":"2009","unstructured":"Kanaris, I., Stamatatos, E.: Learning to recognize webpage genres. Inf. Process. Manage. 45(5), 499\u2013512 (2009)","journal-title":"Inf. Process. Manage."},{"key":"1_CR11","unstructured":"Kennedy, A., Shepherd, M.: Automatic identification of home pages on the web. In: Proceedings of the 38th Annual Hawaii International Conference on System Sciences, HICSS 2005, p. 99c. IEEE (2005)"},{"issue":"13","key":"1_CR12","first-page":"13","volume":"88","author":"KP Kumari","year":"2014","unstructured":"Kumari, K.P., Reddy, A.V., Fatima, S.S.: Web page genre classification: impact of n-gram lengths. Int. J. Comput. Appl. 88(13), 13\u201317 (2014)","journal-title":"Int. J. Comput. Appl."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Levering, R., Cutler, M., Yu, L.: Using visual features for fine-grained genre classification of web pages. In: Proceedings of the 41st Annual Hawaii International Conference on System Sciences, pp. 131\u2013131. IEEE (2008)","DOI":"10.1109\/HICSS.2008.488"},{"issue":"5","key":"1_CR14","doi-asserted-by":"publisher","first-page":"1263","DOI":"10.1016\/j.ipm.2004.06.004","volume":"41","author":"CS Lim","year":"2005","unstructured":"Lim, C.S., Lee, K.J., Kim, G.C.: Multiple sets of features for automatic genre classification of web documents. Inf. Process. Manage. 41(5), 1263\u20131276 (2005)","journal-title":"Inf. Process. Manage."},{"key":"1_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-319-24834-9_2","volume-title":"Intelligent Data Engineering and Automated Learning","author":"G Madjarov","year":"2015","unstructured":"Madjarov, G., Vidulin, V., Dimitrovski, I., Kocev, D.: Web genre classification via hierarchical multi-label classification. In: Jackowski, K., Burduk, R., Walkowiak, K., Wo\u017aniak, M., Yin, H. (eds.) IDEAL 2015. LNCS, vol. 9375, pp. 9\u201317. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24834-9_2"},{"issue":"2","key":"1_CR16","doi-asserted-by":"publisher","first-page":"1567","DOI":"10.1007\/s13198-017-0629-1","volume":"8","author":"R Malhotra","year":"2017","unstructured":"Malhotra, R., Sharma, A.: Quantitative evaluation of web metrics for automatic genre classification of web pages. Int. J. Syst. Assur. Eng. Manage. 8(2), 1567\u20131579 (2017)","journal-title":"Int. J. Syst. Assur. Eng. Manage."},{"key":"1_CR17","unstructured":"Mason, J., Shepherd, M., Duffy, J.: An n-gram based approach to automatically identifying web page genre. In: HICSS, pp. 1\u201310. IEEE Computer Society (2009)"},{"key":"1_CR18","series-title":"Text, Speech and Language Technology","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-9178-9","volume-title":"Genres on the Web: Computational Models and Empirical Studies","author":"A Mehler","year":"2010","unstructured":"Mehler, A., Sharoff, S., Santini, M.: Genres on the Web: Computational Models and Empirical Studies. Text, Speech and Language Technology. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-90-481-9178-9"},{"key":"1_CR19","first-page":"1","volume":"106","author":"PR Mendes J\u00fanior","year":"2016","unstructured":"Mendes J\u00fanior, P.R., et al.: Nearest neighbors distance ratio open-set classifier. Mach. Learn. 106, 1\u201328 (2016)","journal-title":"Mach. Learn."},{"key":"1_CR20","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)"},{"key":"1_CR21","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, pp. 3111\u20133119 (2013)"},{"key":"1_CR22","unstructured":"Nooralahzadeh, F., Brun, C., Roux, C.: Part of speech tagging for French social media data. In: COLING 2014, 25th International Conference on Computational Linguistics, Proceedings of the Conference: Technical Papers, 23\u201329 August 2014, Dublin, Ireland, pp. 1764\u20131772 (2014)"},{"issue":"1","key":"1_CR23","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1177\/0165551516677911","volume":"44","author":"A Onan","year":"2018","unstructured":"Onan, A.: An ensemble scheme based on language function analysis and feature engineering for text genre classification. J. Inf. Sci. 44(1), 28\u201347 (2018)","journal-title":"J. Inf. Sci."},{"issue":"2","key":"1_CR24","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1162\/COLI_a_00052","volume":"37","author":"P Petrenz","year":"2011","unstructured":"Petrenz, P., Webber, B.: Stable classification of text genres. Comput. Linguist. 37(2), 385\u2013393 (2011)","journal-title":"Comput. Linguist."},{"issue":"3","key":"1_CR25","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1007\/s00500-016-2446-x","volume":"21","author":"JP Posadas-Dur\u00e1n","year":"2017","unstructured":"Posadas-Dur\u00e1n, J.P., G\u00f3mez-Adorno, H., Sidorov, G., Batyrshin, I., Pinto, D., Chanona-Hern\u00e1ndez, L.: Application of the distributed document representation in the authorship attribution task for small corpora. Soft Comput. 21(3), 627\u2013639 (2017)","journal-title":"Soft Comput."},{"key":"1_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1007\/978-3-319-24027-5_27","volume-title":"Experimental IR Meets Multilinguality, Multimodality, and Interaction","author":"D Pritsos","year":"2015","unstructured":"Pritsos, D., Stamatatos, E.: The impact of noise in web genre identification. In: Mothe, J., et al. (eds.) CLEF 2015. LNCS, vol. 9283, pp. 268\u2013273. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24027-5_27"},{"key":"1_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10579-018-9418-y","volume":"52","author":"D Pritsos","year":"2018","unstructured":"Pritsos, D., Stamatatos, E.: Open set evaluation of web genre identification. Lang. Resour. Eval. 52, 1\u201320 (2018)","journal-title":"Lang. Resour. Eval."},{"key":"1_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1007\/978-3-642-36973-5_18","volume-title":"Advances in Information Retrieval","author":"DA Pritsos","year":"2013","unstructured":"Pritsos, D.A., Stamatatos, E.: Open-set classification for automated genre identification. In: Serdyukov, P., et al. (eds.) ECIR 2013. LNCS, vol. 7814, pp. 207\u2013217. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-36973-5_18"},{"key":"1_CR29","first-page":"207","volume":"70","author":"PN Priyatam","year":"2013","unstructured":"Priyatam, P.N., Iyengar, S., Perumal, K., Varma, V.: Don\u2019t use a lot when little will do: genre identification using URLs. Res. Comput. Sci. 70, 207\u2013218 (2013)","journal-title":"Res. Comput. Sci."},{"key":"1_CR30","unstructured":"\u0158eh\u016f\u0159ek, R., Sojka, P.: Software framework for topic modelling with large corpora. In: Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, ELRA, Valletta, Malta, pp. 45\u201350, May 2010. http:\/\/is.muni.cz\/publication\/884893\/en"},{"issue":"7","key":"1_CR31","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1002\/asi.20798","volume":"59","author":"MA Rosso","year":"2008","unstructured":"Rosso, M.A.: User-based identification of web genres. J. Am. Soc. Inf. Sci. Technol. 59(7), 1053\u20131072 (2008). https:\/\/doi.org\/10.1002\/asi.20798","journal-title":"J. Am. Soc. Inf. Sci. Technol."},{"key":"1_CR32","unstructured":"Santini, M.: Automatic identification of genre in web pages. Ph.D. thesis, University of Brighton (2007)"},{"key":"1_CR33","series-title":"Text, Speech and Language Technology","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-90-481-9178-9_5","volume-title":"Genres on the Web","author":"M Santini","year":"2011","unstructured":"Santini, M.: Cross-testing a genre classification model for the web. In: Mehler, A., Sharoff, S., Santini, M. (eds.) Genres on the Web. Text, Speech and Language Technology, vol. 42, pp. 87\u2013128. Springer, Dordrecht (2011). https:\/\/doi.org\/10.1007\/978-90-481-9178-9_5"},{"key":"1_CR34","unstructured":"Sharoff, S., Wu, Z., Markert, K.: The Web Library of Babel: evaluating genre collections. In: Proceedings of the Seventh Conference on International Language Resources and Evaluation, pp. 3063\u20133070 (2010)"},{"issue":"3\u20134","key":"1_CR35","first-page":"236","volume":"3","author":"MA Shepherd","year":"2004","unstructured":"Shepherd, M.A., Watters, C.R., Kennedy, A.: Cybergenre: automatic identification of home pages on the web. J. Web Eng. 3(3\u20134), 236\u2013251 (2004)","journal-title":"J. Web Eng."},{"key":"1_CR36","unstructured":"Stewart, J.G.: Genre oriented summarization. Ph.D. thesis, Carnegie Mellon University (2009)"},{"issue":"3\u20134","key":"1_CR37","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s10032-007-0060-2","volume":"10","author":"A Stubbe","year":"2007","unstructured":"Stubbe, A., Ringlstetter, C., Schulz, K.U.: Genre as noise: noise in genre. Int. J. Doc. Anal. Recogn. (IJDAR) 10(3\u20134), 199\u2013209 (2007)","journal-title":"Int. J. Doc. Anal. Recogn. (IJDAR)"},{"key":"1_CR38","unstructured":"Vidulin, V., Lu\u0161trek, M., Gams, M.: Using genres to improve search engines. In: Proceedings of the International Workshop Towards Genre-Enabled Search Engines, pp. 45\u201351 (2007)"},{"key":"1_CR39","unstructured":"Worsham, J., Kalita, J.: Genre identification and the compositional effect of genre in literature. In: Proceedings of the 27th International Conference on Computational Linguistics, pp. 1963\u20131973 (2018)"},{"key":"1_CR40","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/978-3-642-24434-6_23","volume-title":"Web Information System Engineering","author":"J Zhu","year":"2011","unstructured":"Zhu, J., Zhou, X., Fung, G.: Enhance web pages genre identification using neighboring pages. In: Bouguettaya, A., Hauswirth, M., Liu, L. (eds.) WISE 2011. LNCS, vol. 6997, pp. 282\u2013289. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-24434-6_23"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-15719-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T17:33:08Z","timestamp":1710264788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-15719-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030157180","9783030157197"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-15719-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"7 April 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cologne","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 April 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"41","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ecir2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}