{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T05:04:49Z","timestamp":1740632689818,"version":"3.38.0"},"publisher-location":"Dordrecht","reference-count":27,"publisher":"Springer Netherlands","isbn-type":[{"type":"print","value":"9789048191772"},{"type":"electronic","value":"9789048191789"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-90-481-9178-9_6","type":"book-chapter","created":{"date-parts":[[2010,9,30]],"date-time":"2010-09-30T18:07:57Z","timestamp":1285870077000},"page":"129-147","source":"Crossref","is-referenced-by-count":1,"title":["Formulating Representative Features with Respect to Genre Classification"],"prefix":"10.1007","author":[{"given":"Yunhyong","family":"Kim","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seamus","family":"Ross","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2010,8,16]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bagdanov, A., and M. Worring. 2001. Fine-grained document genre classification using first order random graphs. In Proceedings of the 2001 Sixth International Conference on Document Analysis and Recognition (ICDAR\u201901), 79\u201390. Seattle, WA. USA. http:\/\/doi.ieeecomputersociety.org\/10.1109\/ICDAR.2001.953759","DOI":"10.1109\/ICDAR.2001.953759"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Barbu, E., P. Heroux, S. Adam, and E. Turpin. 2005. Clustering document images using a bag of symbols representation. In Proceedings of the 2005 Eight International Conference on Document Analysis and Recognition (ICDAR\u201905), 1216\u20131220. Seoul, Korea. http:\/\/doi.ieeecomputersociety.org\/10.1109\/ICDAR.2001.953759","DOI":"10.1109\/ICDAR.2005.75"},{"key":"6_CR3","unstructured":"Bekkerman, R., A. McCallum, and G. Huang. 2004. Automatic categorization of email into folders: Benchmark experiments on Enron and Sri corpora. Technical Report IR-418, Center for Intelligent Information Retrieval, UMASS. http:\/\/www . cs.umass.edu\/\\homedirmccallum\/papers\/foldering-tr05.pdf"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Berninger, V.F., Y. Kim, and S. Ross. 2009. Building a document genre corpus: A profile of the KRYS I corpus. In Proceedings of Corpus Profiling Workshop with \u2018BCS-IRSG Workshop on Corpus Profiling\u2019. http:\/\/www.bcs.org\/server.php?show=conWebDoc.26115","DOI":"10.14236\/ewic\/IRSG2008.2"},{"key":"6_CR5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511519871","volume-title":"Dimensions of register variation: a cross-linguistic comparison.","author":"D. Biber","year":"1995","unstructured":"Biber, D. 1995. Dimensions of register variation: a cross-linguistic comparison. New York, NY: Cambridge University Press."},{"issue":"2","key":"6_CR6","first-page":"102","volume":"49","author":"A. Bookstein","year":"1998","unstructured":"Bookstein, A., S.T. Klein, and T. Raita. 1998. Clumping properties of content-bearing words. Journal of the American Society of Information Science 49(2):102\u2013114.","journal-title":"Journal of the American Society of Information Science"},{"key":"6_CR7","unstructured":"Dc-dot: UKOLN Dublin Core Metadata Editor (webpage last updated Aug 2000). http:\/\/www.ukoln.ac.uk\/metadata\/dcdot\/"},{"key":"6_CR8","unstructured":"De Roeck, A., A. Sarkar, and P. Garthwaite. 2004. Frequent term distribution measures for dataset profiling. Technical Report 2004\/2006, Faculty of Mathematics and Computing, Open University. Milton Keynes. http:\/\/computing-reports.open.ac.uk\/index.php\/"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Dong, L., C. Watters, J. Duffy, and M. Shepherd. 2008. An examination of genre attributes for web page classification. In Proceedings 41st Hawaiian International Conference on System Sciences. IEEE Computer Society Press. Waikoloa, Big Island, HI, USA. http:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp=&arnumber=4438836","DOI":"10.1109\/HICSS.2008.53"},{"issue":"11","key":"6_CR10","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1002\/asi.20427","volume":"57","author":"A. Finn","year":"2006","unstructured":"Finn, A., and N. Kushmerick. 2006. Learning to classify documents according to genre. Journal of American Society for Information Science and Technology 57(11):1506\u20131518.","journal-title":"Journal of American Society for Information Science and Technology"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Giuffrida, G., E. Shek, and J. Yang. 2000. Knowledge-based metadata extraction from PostScript Files. In Proceedings 5th ACM International Conference on Digital Libraries, 77\u201384. San Antonio, TX, USA. http:\/\/portal.acm.org\/citation.cfm?id=336597.336639","DOI":"10.1145\/336597.336639"},{"key":"6_CR12","unstructured":"Han, H., L. Giles, E. Manavoglu, H. Zha, Z. Zhang, and E.A. Fox. 2003. Automatic document metadata extraction using support vector machines. In Proceedings of the 3rd ACM\/IEEE-CS joint conference on Digital libraries, 77\u201384. Houston, TX, USA. http:\/\/portal.acm.org\/citation.cfm?id=827146"},{"key":"6_CR13","doi-asserted-by":"crossref","unstructured":"Kanaris, I., and E. Stamatatos. 2007. Webpage genre identification using variable-length character n-grams. In Proceedings 19th IEEE International Conference on Tools with Artificial Intelligence. Patras, GR. http:\/\/portal.acm.org\/citation.cfm?id=1337285","DOI":"10.1109\/ICTAI.2007.107"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Karlgren, J., and D. Cutting. 1994. Recognizing text genres with simple metric using discriminant analysis. In Proceedings 15th Conference on Computational Linguistics 2:1071\u20131075. Kyoto, Japan.","DOI":"10.3115\/991250.991324"},{"key":"6_CR15","first-page":"460","volume-title":"ECIR 2006 (London, UK)","author":"S.W. Ke","year":"2006","unstructured":"Ke, S.W., C. Bowerman, and M. Oakes. 2006. PERC: A personal email classifier. In ECIR 2006 (London, UK), eds. M. Lalmas et al., LNCS 3936, 460\u2013463, Heidelberg: Springer-Verlag, http:\/\/www.springerlink.com\/content\/r27700t736786455\/fulltext.pdf"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Kessler, G., B. Nunberg, and H. Schuetze. 1997. Automatic detection of text genre. In Proceedings 35th Annual Meeting ACL, 32\u201338. Madrid, Spain.","DOI":"10.3115\/976909.979622"},{"key":"6_CR17","doi-asserted-by":"publisher","first-page":"S172","DOI":"10.2481\/dsj.6.S172","volume":"6","author":"Y. Kim","year":"2007","unstructured":"Kim, Y., and S. Ross. 2007a. Detecting family resemblance: Automated genre classification. CODATA Data Science Journal 6:S172\u2013S183. ISSN: 1683\u20131470. http:\/\/www.jstage.jst.go.jp\/article\/dsj\/6\/0\/S172\/_pdf","journal-title":"CODATA Data Science Journal"},{"key":"6_CR18","first-page":"248","volume-title":"In Digital libraries: R&D (Tirrenia, Italy)","author":"Y. Kim","year":"2007","unstructured":"Kim, Y., and S. Ross. 2007b. Searching for ground truth: A stepping stone in automated genre classification. In Digital libraries: R&D (Tirrenia, Italy), eds. C. Thanos, F. Borri, and L. Candela, LNCS 4877, 248\u2013261, Heidelberg: Springer-Verlag, http:\/\/www.springerlink.com\/content\/lt760613m2731723"},{"key":"6_CR19","volume-title":"Foundations of statistical language processing.","author":"C. Manning","year":"1999","unstructured":"Manning, C., and H. Schutze. 1999. Foundations of statistical language processing. Cambridge, MA: MIT Press."},{"key":"6_CR20","unstructured":"McCallum, A. 1996. Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering. http:\/\/www.cs.cmu.edu\/ \\verb1~11mccallum\/bow"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Rauber, A., and A. M\u00fcller-K\u00f6gler. 2001. Integrating automatic genre analysis into digital libraries. In Proceedings of the 1st ACM\/IEEE-CS Joint Conference on Digital Libraries, 1\u201310. Roanoke, VA, USA. http:\/\/doi.acm.org\/10.1145\/379437.379439","DOI":"10.1145\/379437.379439"},{"key":"6_CR22","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1163\/9789004334113_020","volume-title":"New frontiers of corpus research: Papers from the 21st International Conference on English Language Research on Computerized Corpora, Sydney 2000","author":"P. Rayson","year":"2002","unstructured":"Rayson, P., A. Wilson, and G. Leech. 2002. Grammatical word class variation within the British National Corpus sampler. In New frontiers of corpus research: Papers from the 21st International Conference on English Language Research on Computerized Corpora, Sydney 2000, eds. P. Peters, P. Collins, and A. Smith, 295\u2013306. Amsterdam: Rodopi."},{"issue":"4","key":"6_CR23","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1007\/s00799-004-0099-3","volume":"5","author":"S. Ross","year":"2005","unstructured":"Ross, S., and M. Hedstrom. 2005. Preservation research and sustainable digital libraries. International Journal of Digital Libraries 5(4):317\u2013325.","journal-title":"International Journal of Digital Libraries"},{"key":"6_CR24","unstructured":"Santini, M. 2007. Automatic identification of genre in web pages. PhD Thesis, University of Brighton, Brighton. http:\/\/www.itri.brighton.ac.uk\/ \\homedirMarina.Santini\/ MSantini\\_PhD\\_Thesis.zip"},{"key":"6_CR25","unstructured":"Thoma, G. 2001. Automating the production of bibliographic records. Technical report, Lister Hill National Center for Biomedical Communication, US National Library of Medicine. http:\/\/archive.nlm.nih.gov\/pubs\/thoma\/mars2001.php"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Yang, Y., J. Zhang, and B. Kisiel. 2003. A scalability analysis of classifiers in text categorization. In Proceedings 26th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, 96\u2013103. Toronto, ON, CA. http:\/\/doi.acm.org\/10.1145\/860435.860455","DOI":"10.1145\/860435.860455"},{"key":"6_CR27","volume-title":"Data mining: Practical machine learning tools and techniques","author":"H.I. Witten","year":"2005","unstructured":"Witten, H.I., and E. Frank. 2005. Data mining: Practical machine learning tools and techniques, 2nd ed. San Francisco, CA: Morgan Kaufmann.","edition":"2"}],"container-title":["Text, Speech and Language Technology","Genres on the Web"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-90-481-9178-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T04:25:02Z","timestamp":1740543902000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-90-481-9178-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9789048191772","9789048191789"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-90-481-9178-9_6","relation":{},"ISSN":["1386-291X"],"issn-type":[{"type":"print","value":"1386-291X"}],"subject":[],"published":{"date-parts":[[2010]]}}}