{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T11:13:55Z","timestamp":1760267635026,"version":"3.41.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2018,6,26]],"date-time":"2018-06-26T00:00:00Z","timestamp":1529971200000},"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":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1007\/s10579-018-9418-y","type":"journal-article","created":{"date-parts":[[2018,6,26]],"date-time":"2018-06-26T14:03:48Z","timestamp":1530021828000},"page":"949-968","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Open set evaluation of web genre identification"],"prefix":"10.1007","volume":"52","author":[{"given":"Dimitrios","family":"Pritsos","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Efstathios","family":"Stamatatos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,26]]},"reference":[{"key":"9418_CR1","unstructured":"Abramson, M., & Aha, D.W. (2012) 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."},{"key":"9418_CR2","unstructured":"Asheghi, N. R. (2015). Human annotation and automatic detection of web genres. Ph.D. thesis, University of Leeds."},{"key":"9418_CR3","unstructured":"Asheghi, N. R,, Markert, K., & Sharoff, S. (2014) Semi-supervised graph-based genre classification for web pages. TextGraphs-9 p\u00a039."},{"key":"9418_CR4","unstructured":"Bishop, C. (2006). Pattern recognition and machine learning. (pp 331\u2013336). New York: Springer."},{"key":"9418_CR5","unstructured":"Boese, E. S., & Howe, A. E. (2005). 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."},{"key":"9418_CR6","unstructured":"Braslavski, P. (2007). Combining relevance and genre-related rankings: An exploratory study. In: Proceedings of the international workshop towards genreenabled search engines: The impact of NLP pp 1\u20134."},{"issue":"6","key":"9418_CR7","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1016\/S0031-3203(02)00121-8","volume":"36","author":"R Bryll","year":"2003","unstructured":"Bryll, R., Gutierrez-Osuna, R., & Quek, F. (2003). Attribute bagging: Improving accuracy of classifier ensembles by using random feature subsets. Pattern Recognition, 36(6), 1291\u20131302.","journal-title":"Pattern Recognition"},{"key":"9418_CR8","unstructured":"Crowston, K., Kwa\u015bnik, B., & Rubleske, J. (2011). Problems in the use-centered development of a taxonomy of web genres. In: Genres on the Web, (pp 69\u201384), Springer."},{"issue":"3","key":"9418_CR9","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1007\/s11280-009-0063-7","volume":"12","author":"GT Assis De","year":"2009","unstructured":"De Assis, G. T., Laender, A. H., Gon\u00e7alves, M. A., & Da Silva, A. S. (2009). A genre-aware approach to focused crawling. World Wide Web, 12(3), 285\u2013319.","journal-title":"World Wide Web"},{"key":"9418_CR10","doi-asserted-by":"crossref","unstructured":"Dong, L., Watters, C., Duffy, J., & Shepherd, M. (2006). Binary cybergenre classification using theoretic feature measures. In Web Intelligence, 2006. WI 2006. IEEE\/WIC\/ACM International Conference on (pp. 313\u2013316). IEEE","DOI":"10.1109\/WI.2006.50"},{"issue":"8","key":"9418_CR12","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/34.709601","volume":"20","author":"TK Ho","year":"1998","unstructured":"Ho, T. K. (1998). The random subspace method for constructing decision forests. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8), 832\u2013844.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9418_CR13","unstructured":"Jebari, C. (2014). 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."},{"key":"9418_CR14","first-page":"13","volume":"54","author":"C Jebari","year":"2015","unstructured":"Jebari, C. (2015a). A combination based on owa operators for multi-label genre classification of web pages. Procesamiento del Lenguaje Natural, 54, 13\u201320.","journal-title":"Procesamiento del Lenguaje Natural"},{"issue":"3\u20134","key":"9418_CR15","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1504\/IJMHEUR.2015.074426","volume":"4","author":"C Jebari","year":"2015","unstructured":"Jebari, C. (2015b). Enhanced and combined centroid-based approach for multi-label genre classification of web pages. International Journal of Metaheuristics, 4(3\u20134), 220\u2013243.","journal-title":"International Journal of Metaheuristics"},{"issue":"2","key":"9418_CR16","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1145\/1041394.1041395","volume":"38","author":"Hideo Joho","year":"2004","unstructured":"Joho, H., & Sanderson, M. (2004). The spirit collection: An overview of a large web collection. In:textitACM SIGIR Forum (Vol. 38, pp. 57\u201361).ACM.","journal-title":"ACM SIGIR Forum"},{"issue":"5","key":"9418_CR17","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. (2009). Learning to recognize webpage genres. Information Processing & Management, 45(5), 499\u2013512.","journal-title":"Information Processing & Management"},{"key":"9418_CR18","unstructured":"Kennedy, A., & Shepherd, M. (2005). Automatic identification of home pages on the web. In: Proceedings of the 38th annual Hawaii international conference on system sciences, 2005. HICSS\u201905,(pp 99c\u201399c). IEEE."},{"issue":"1","key":"9418_CR20","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s10579-009-9111-2","volume":"45","author":"M Koppel","year":"2011","unstructured":"Koppel, M., Schler, J., & Argamon, S. (2011). Authorship attribution in the wild. Language Resources and Evaluation, 45(1), 83\u201394.","journal-title":"Language Resources and Evaluation"},{"issue":"1","key":"9418_CR19","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1002\/asi.22954","volume":"65","author":"M Koppel","year":"2014","unstructured":"Koppel, M., & Winter, Y. (2014). Determining if two documents are written by the same author. Journal of the Association for Information Science and Technology, 65(1), 178\u2013187.","journal-title":"Journal of the Association for Information Science and Technology"},{"issue":"13","key":"9418_CR21","doi-asserted-by":"publisher","first-page":"13","DOI":"10.5120\/15675-4423","volume":"88","author":"KP Kumari","year":"2014","unstructured":"Kumari, K. P., Reddy, A. V., & Fatima, S. S. (2014). Web page genre classification: Impact of n-gram lengths. International Journal of Computer Applications, 88(13), 13\u201317.","journal-title":"International Journal of Computer Applications"},{"key":"9418_CR22","unstructured":"Levering, R., Cutler, M., & Yu, L. (2008). 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."},{"issue":"5","key":"9418_CR23","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. (2005). Multiple sets of features for automatic genre classification of web documents. Information Processing and Management, 41(5), 1263\u20131276.","journal-title":"Information Processing and Management"},{"key":"9418_CR24","unstructured":"Madjarov, G., Vidulin, V., Dimitrovski, I., & Kocev, D. (2015). Web genre classification via hierarchical multi-label classification. In: Intelligent Data Engineering and Automated Learning\u2013IDEAL 2015, (pp 9\u201317). Springer."},{"key":"9418_CR25","doi-asserted-by":"crossref","unstructured":"Mason, J., Shepherd, M., & Duffy, J. (2009a). An n-gram based approach to automatically identifying web page genre. In: hicss, IEEE Computer Society, pp 1\u201310.","DOI":"10.1109\/HICSS.2009.68"},{"key":"9418_CR26","unstructured":"Mason, J., Shepherd, M., & Duffy, J. (2009b). Classifying web pages by genre: A distance function approach. In: Proceedings of the 5th international conference on web information systems and technologies (WEBIST 2009)."},{"key":"9418_CR27","unstructured":"Mehler, A., Sharoff, S., & Santini, M. (2010). Genres on the Web: Computational models and empirical studies. Speech and Language Technology, Springer: Text."},{"key":"9418_CR28","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1007\/s10994-016-5610-8","volume":"106","author":"PR Mendes\u00a0J\u00fanior","year":"2005","unstructured":"Mendes\u00a0J\u00fanior, P. R., de\u00a0Souza, R. M., Werneck, R. d. O., Stein, B. V., Pazinato, D. V., de\u00a0Almeida, W. R., Penatti, O. A., Torres, R. d. S., Rocha, A. (2017). Nearest neighbors distance ratio open-set classifier. Machine Learning, 106, 359\u2013386. https:\/\/doi.org\/10.1007\/s10994-016-5610-8 .","journal-title":"Machine Learning"},{"key":"9418_CR11","unstructured":"Meyer\u00a0zu Eissen, S., & Stein, B. (2004). Genre classification of web pages. In: KI 2004: Advances in Artificial Intelligence pp 256\u2013269."},{"key":"9418_CR29","unstructured":"Nooralahzadeh, F., Brun, C., & Roux, C. (2014). Part of speech tagging for french social media data. In: COLING 2014, 25th international conference on computational linguistics, proceedings of the conference: technical papers, August 23\u201329, 2014, Dublin, Ireland, pp 1764\u20131772."},{"issue":"2","key":"9418_CR30","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. (2011). Stable classification of text genres. Computational Linguistics, 37(2), 385\u2013393.","journal-title":"Computational Linguistics"},{"key":"9418_CR31","unstructured":"Pritsos, D., & Stamatatos, E. (2015). The impact of noise in web genre identification. In: Experimental IR meets multilinguality, multimodality, and interaction, (pp 268\u2013273). Springer."},{"key":"9418_CR32","unstructured":"Pritsos, D.A., & Stamatatos, E. (2013). Open-set classification for automated genre identification. In: Advances in information retrieval, (pp 207\u2013217). Springer."},{"key":"9418_CR33","first-page":"207","volume":"70","author":"PN Priyatam","year":"2013","unstructured":"Priyatam, P. N., Iyengar, S., Perumal, K., & Varma, V. (2013). Don\u2019t use a lot when little will do: Genre identification using urls. Research in Computing Science, 70, 207\u2013218.","journal-title":"Research in Computing Science"},{"issue":"7","key":"9418_CR34","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1002\/asi.20798","volume":"59","author":"MA Rosso","year":"2008","unstructured":"Rosso, M. A. (2008). User-based identification of web genres. Journal of the American Society for Information Science and Technology, 59(7), 1053\u20131072. https:\/\/doi.org\/10.1002\/asi.20798 .","journal-title":"Journal of the American Society for Information Science and Technology"},{"key":"9418_CR35","unstructured":"Santini, M. (2007). Automatic identification of genre in web pages. Ph.D. thesis, University of Brighton."},{"key":"9418_CR36","unstructured":"Santini, M. (2011). Cross-testing a genre classification model for the web. In: Genres on the Web, (pp 87\u2013128). Springer."},{"issue":"7","key":"9418_CR37","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1109\/TPAMI.2012.256","volume":"35","author":"WJ Scheirer","year":"2013","unstructured":"Scheirer, W. J., de Rezende, Rocha A., Sapkota, A., & Boult, T. E. (2013). Toward open set recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(7), 1757\u20131772.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"9418_CR38","unstructured":"Scholkopf, B., Platt, J., Shawe-Taylor, J., Smola, A., Williamson, R. (1999). Estimating the support of a high-dimensional distribution. Technical Report MSR-TR-99-87."},{"key":"9418_CR39","unstructured":"Sharoff, S., Wu, Z., & Markert, K. (2010). The web library of babel: Evaluating genre collections. In: Proceedings of the seventh conference on international language resources and evaluation, pp 3063\u20133070."},{"issue":"3\u20134","key":"9418_CR40","first-page":"236","volume":"3","author":"MA Shepherd","year":"2004","unstructured":"Shepherd, M. A., Watters, C. R., & Kennedy, A. (2004). Cybergenre: Automatic identification of home pages on the web. Journal of Web Engineering, 3(3\u20134), 236\u2013251.","journal-title":"Journal of Web Engineering"},{"issue":"3\u20134","key":"9418_CR41","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. (2007). Genre as noise: Noise in genre. International Journal of Document Analysis and Recognition (IJDAR), 10(3\u20134), 199\u2013209.","journal-title":"International Journal of Document Analysis and Recognition (IJDAR)"},{"key":"9418_CR42","unstructured":"Vidulin, V., Lu\u0161trek, M., & Gams, M. (2007). Using genres to improve search engines. In: Proceedings of the international workshop towards genre-enabled search engines, pp 45\u201351."},{"key":"9418_CR43","unstructured":"Zhu, J., Zhou, X., & Fung, G. (2011). Enhance web pages genre identification using neighboring pages. In: Web information system engineering\u2013WISE 2011, (pp 282\u2013289). Springer."}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-018-9418-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-9418-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-018-9418-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,5]],"date-time":"2025-07-05T10:12:41Z","timestamp":1751710361000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-018-9418-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,26]]},"references-count":43,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["9418"],"URL":"https:\/\/doi.org\/10.1007\/s10579-018-9418-y","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2018,6,26]]},"assertion":[{"value":"26 June 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}