{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T20:01:41Z","timestamp":1771704101113,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2015,7,7]],"date-time":"2015-07-07T00:00:00Z","timestamp":1436227200000},"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":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2016,5]]},"DOI":"10.1007\/s10618-015-0428-8","type":"journal-article","created":{"date-parts":[[2015,7,6]],"date-time":"2015-07-06T11:38:49Z","timestamp":1436182729000},"page":"550-575","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Exploiting link structure for web page genre identification"],"prefix":"10.1007","volume":"30","author":[{"given":"Jia","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Qing","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Shoou-I","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Wai Hung","family":"Wong","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,7,7]]},"reference":[{"key":"428_CR1","unstructured":"Abramson M, Aha DW (2012) What\u2019s in a URL? genre classification from URLs. In: Workshops at the 26th Advancement of Artificial Intelligence (AAAI) Conference on Artificial Intelligence, pp. 1\u20138"},{"issue":"1","key":"428_CR2","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1145\/383034.383035","volume":"1","author":"A Arasu","year":"2001","unstructured":"Arasu A, Cho J, Garcia-Molina H, Paepcke A, Raghavan S (2001) Searching the web. ACM Trans Internet Technol 1(1):2\u201343","journal-title":"ACM Trans Internet Technol"},{"key":"428_CR3","volume-title":"Advances in kernel methods: support vector learning","author":"S Bernhard","year":"1998","unstructured":"Bernhard S, Burges JC, Smola AJ (1998) Advances in kernel methods: support vector learning. The MIT Press, Cambridge"},{"key":"428_CR4","unstructured":"Bjroneborn L (2011) Genre connectivity and genre drift in a web of genres. In: Genres on the Web: Computational Models and Empirical Studies, pp. 255\u2013274"},{"key":"428_CR5","doi-asserted-by":"crossref","unstructured":"Boese E, Howe A (2005) Effects of web document evolution on genre classification. In: Proceedings of the ACM 14th Conference on Information and Knowledge Management, pp. 632\u2013639","DOI":"10.1145\/1099554.1099715"},{"key":"428_CR6","doi-asserted-by":"crossref","unstructured":"Chen G, Choi B (2008) Web page genre classification. In: Proceedings of the 2008 ACM Symposium on Applied Computing, pp. 2353\u20132357","DOI":"10.1145\/1363686.1364247"},{"key":"428_CR7","doi-asserted-by":"crossref","unstructured":"Dong L, Watters C, Duffy J, Shepherd M (2008) An examination of genre attributes for web page classification. In: Proceedings of the 41th Annual Hawaii International Conference on System Sciences, pp. 129\u2013138","DOI":"10.1109\/HICSS.2008.53"},{"issue":"11","key":"428_CR8","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1002\/asi.20427","volume":"57","author":"A Finn","year":"2006","unstructured":"Finn A, Kushmerick N (2006) Learning to classify documents according to genre. J Am Soc Inf Sci Technol 57(11):257\u2013262","journal-title":"J Am Soc Inf Sci Technol"},{"key":"428_CR9","volume-title":"Algorithms for clustering data","author":"AK Jain","year":"1988","unstructured":"Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall, Englewood Cliffs"},{"issue":"1","key":"428_CR10","doi-asserted-by":"crossref","first-page":"73","DOI":"10.21248\/jlcl.24.2009.114","volume":"24","author":"C Jebari","year":"2009","unstructured":"Jebari C (2009) A new centroid-based approach for genre categorization of web pages. J Lang Technol Comput Linguist 24(1):73\u201396","journal-title":"J Lang Technol Comput Linguist"},{"key":"428_CR11","doi-asserted-by":"crossref","unstructured":"Jeh G, Widom J (2002) Simrank: a measure of structural-context similarity. In: Proceedings of the 8th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 538\u2013543","DOI":"10.1145\/775047.775126"},{"key":"428_CR12","doi-asserted-by":"crossref","unstructured":"Kanaris I, Stamatatos E (2007) Web page genre identification using variable-length character n-grams. In: Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence, vol 7(1), pp. 3\u201310","DOI":"10.1109\/ICTAI.2007.107"},{"key":"428_CR13","doi-asserted-by":"crossref","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, pp. 99\u2013108","DOI":"10.1109\/HICSS.2005.114"},{"key":"428_CR14","doi-asserted-by":"crossref","unstructured":"Kessler B, Nunberg G, Shutze H (1997) Automatic detection of text genre. In: Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics, pp. 32\u201338","DOI":"10.3115\/976909.979622"},{"key":"428_CR15","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1007\/978-90-481-9178-9_6","volume":"42","author":"Y Kim","year":"2011","unstructured":"Kim Y, Ross S (2011) Formulating representative features with respect to genre classification. Genres Web Comput Model Empir Stud 42:129\u2013147","journal-title":"Genres Web Comput Model Empir Stud"},{"issue":"4es","key":"428_CR16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1145\/345966.345982","volume":"31","author":"JM Kleinberg","year":"1999","unstructured":"Kleinberg JM (1999) Hubs, authorities, and communities. ACM Comput Surv 31(4es):5","journal-title":"ACM Comput Surv"},{"issue":"5","key":"428_CR17","doi-asserted-by":"crossref","first-page":"604","DOI":"10.1145\/324133.324140","volume":"46","author":"JM Kleinbery","year":"1999","unstructured":"Kleinbery JM (1999) Authoritative sources in a hyperlinked environment. J ACM 46(5):604\u2013632","journal-title":"J ACM"},{"issue":"10","key":"428_CR18","first-page":"24","volume":"53","author":"KP Kumari","year":"2012","unstructured":"Kumari KP, Reddy A (2012) Performance improvement of web page genre classification. Int J Comput Appl 53(10):24\u201327","journal-title":"Int J Comput Appl"},{"issue":"2","key":"428_CR19","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S0031-3203(99)00223-X","volume":"34","author":"LI Kuncheva","year":"2001","unstructured":"Kuncheva LI, Bezdek JC, Duin RP (2001) Decision templates for multiple classifier fusion. Pattern Recognit 34(2):299\u2013314","journal-title":"Pattern Recognit"},{"key":"428_CR20","doi-asserted-by":"crossref","unstructured":"Laender AHF, Goncalves MA, Cota RG, Ferreira AA, Santos RLT, Silva AJC (2008) Keeping a digital library clean: new solutions to old problems. In: Proceedings of the 8th ACM Symposium on Document Engineering, pp. 257\u2013262","DOI":"10.1145\/1410140.1410195"},{"issue":"1","key":"428_CR21","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/BF00134114","volume":"41","author":"L Lam","year":"1996","unstructured":"Lam L, Suen CY (1996) Majority vote of even and odd experts in a polychotomous choice situation. Theory Decision 41(1):13\u201336","journal-title":"Theory Decision"},{"key":"428_CR22","doi-asserted-by":"crossref","unstructured":"Lee Y, Myaeng S (2002) Text genre classification with genre-revealing and subject-revealing features. In: Proceedings of the 25th ACM Special Interest Group on Information Retrieval (SIGIR) Conference on Research and Development in Information Retrieval, pp. 145\u2013150","DOI":"10.1145\/564376.564403"},{"key":"428_CR23","doi-asserted-by":"crossref","unstructured":"Lin Z, King I, Ly MR (2006) Pagesim: a novel link-based similarity measure for the World Wide Web. In: Proceedings of the 5th International Conference on Web Intelligence, pp. 687\u2013693","DOI":"10.1109\/WI.2006.127"},{"key":"428_CR24","first-page":"22","volume":"11","author":"J Lovins","year":"1968","unstructured":"Lovins J (1968) Development of a stemming algorithm. Mech Transl Comput Linguist 11:22\u201331","journal-title":"Mech Transl Comput Linguist"},{"key":"428_CR25","doi-asserted-by":"crossref","unstructured":"Mason JE, Shepherd M, Duffy J, Keselj V, Watters C (2010) An n-gram based approach to multi-labeled web page genre classification. In: Proceedings of the 46th Hawaii International Conference on System Sciences, pp. 1\u201310","DOI":"10.1109\/HICSS.2010.58"},{"key":"428_CR26","unstructured":"Mehler A, Gleim R, Wegner A (2007) Structural uncertainty of hypertext types. an empirical study. Proceedings of the International Workshop:Towards Genre-Enabled Search Engines: The Impact of NLP, pp. 13\u201319"},{"key":"428_CR27","volume-title":"Machine learning","author":"T Mitchell","year":"1997","unstructured":"Mitchell T (1997) Machine learning. McGraw-Hill, New York"},{"key":"428_CR28","doi-asserted-by":"crossref","unstructured":"Orrite C, Rodriguez M, Martinez F, Fairhurst M (2008) Classifier ensemble generation for the majority vote rule. In: Proceedings of the 13th Iberoamerican Congress on Pattern Recognition, pp. 340\u2013347","DOI":"10.1007\/978-3-540-85920-8_42"},{"key":"428_CR29","doi-asserted-by":"crossref","unstructured":"Pereira DA, Ribeiro BN, Ziviani N, Alberto HF, Goncalves AM, Ferreira AA (2009) Using web information for author name disambiguation. In: Proceedings of the 9th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 49\u201358","DOI":"10.1145\/1555400.1555409"},{"key":"428_CR30","doi-asserted-by":"crossref","unstructured":"Pritsos D, Stamatatos E (2013) Open-set classification for automated genre identification. In: Proceedings of the 35th European Conference on Information Retrieval Research, pp. 207\u2013217","DOI":"10.1007\/978-3-642-36973-5_18"},{"key":"428_CR31","doi-asserted-by":"crossref","unstructured":"Qi X, Davison B (2008) Classifiers without borders: incorporating fielded text from neighboring web pages. In: Proceedings of the 31st Annual International ACM Special Interest Group on Information Retrieval (SIGIR) Conference on Research and Development on Information Retrieval, pp. 643\u2013650","DOI":"10.1145\/1390334.1390443"},{"key":"428_CR32","volume-title":"Introduction to modern information retrieval","author":"G Salton","year":"1986","unstructured":"Salton G, McGill MJ (1986) Introduction to modern information retrieval. McGraw-Hill, New York"},{"key":"428_CR33","unstructured":"Santini M (2006) Common criteria for genre classification: Annotation and granularity. In: Workshop on Text-based Information Retrieval. In Conjunction with the 21st European Conference on Artificial Intelligence(ECAI), pp. 1\u20136"},{"key":"428_CR34","doi-asserted-by":"crossref","unstructured":"Santini M (2007) Characterizing genres of web pages: Genre hybridism and individualization. In: Proceedings of the 40th Annual Hawaii International Conference on System Sciences, pp. 71\u201380","DOI":"10.1109\/HICSS.2007.124"},{"issue":"1","key":"428_CR35","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/505282.505283","volume":"34","author":"F Sebastiani","year":"2002","unstructured":"Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv (CSUR) 34(1):1\u201347","journal-title":"ACM Comput Surv (CSUR)"},{"key":"428_CR36","unstructured":"Sharoff S, Wu Z, Markert K (2010) The web library of babel: evaluating genre collections. In: Proceedings of the 8th International Conference on Language Resources and Evaluation, pp. 3063\u20133070"},{"key":"428_CR37","doi-asserted-by":"crossref","unstructured":"Stamatatos E, Fakotakis N, Kokkinakis G (2000) Text genre detection using common word frequencies. In: Proceedings of the 18th Internation Conference on Computational Linguistics, pp. 808\u2013814","DOI":"10.3115\/992730.992763"},{"key":"428_CR38","unstructured":"Stein B, zu\u00a0Eissen SM (2006) Is web genre identification feasible? In: 17th European Conference on Artificial Intelligence (ECAI 06), pp. 815\u2013816"},{"key":"428_CR39","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-2440-0","volume-title":"The nature of statistical learning","author":"V Vapnik","year":"1995","unstructured":"Vapnik V (1995) The nature of statistical learning. Springer, New York"},{"key":"428_CR40","doi-asserted-by":"crossref","unstructured":"Yang Y, Liu X (1999) A re-examination of text categorization methods. In: Proceedings of the 22nd Annual International ACM Special Interest Group on Information Retrieval (SIGIR) Conference on Research and Development in Information Retrieval, pp. 42\u201349","DOI":"10.1145\/312624.312647"},{"key":"428_CR41","doi-asserted-by":"crossref","unstructured":"Zhu J, Zhou X, Fung G (2011) Enhance web pages genre identification using neighboring pages. In: Proceedings of the 12th International Conference on Web Information System Engineering, pp. 282\u2013289","DOI":"10.1007\/978-3-642-24434-6_23"},{"key":"428_CR42","unstructured":"Zu\u00a0Eissen SM, Stein B (2004) Genre classification of web pages: user study and feasibility analysis. In: 27th Annual German Conference on AI (KI 04), pp. 256\u2013269"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-015-0428-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10618-015-0428-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-015-0428-8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,12]],"date-time":"2023-08-12T01:43:14Z","timestamp":1691804594000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10618-015-0428-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,7]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2016,5]]}},"alternative-id":["428"],"URL":"https:\/\/doi.org\/10.1007\/s10618-015-0428-8","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,7,7]]}}}