{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T00:36:20Z","timestamp":1725496580764},"publisher-location":"Berlin, Heidelberg","reference-count":24,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540770879"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77088-6_24","type":"book-chapter","created":{"date-parts":[[2007,11,24]],"date-time":"2007-11-24T01:19:47Z","timestamp":1195867187000},"page":"248-261","source":"Crossref","is-referenced-by-count":2,"title":["Searching for Ground Truth: A Stepping Stone in Automating Genre Classification"],"prefix":"10.1007","author":[{"given":"Yunhyong","family":"Kim","sequence":"first","affiliation":[]},{"given":"Seamus","family":"Ross","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"24_CR1","doi-asserted-by":"crossref","unstructured":"Bagdanov, A., Worring, M.: Fine-grained document genre classification using first order random graphs. In: Proceedings 6th International Conference on Document Analysis and Recognition, pp. 79\u201383 (2001) ISBN 0-7695-1263-1","DOI":"10.1109\/ICDAR.2001.953759"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Barbu, E., Heroux, P., Adam, S., Turpin, E.: Clustering document images using a bag of symbols representation. In: Proceedings 8th International Conference on Document Analysis and Recognition, pp. 1216-1220 (2005) ISBN\u00a0ISSN 1520-5263","DOI":"10.1109\/ICDAR.2005.75"},{"key":"24_CR3","unstructured":"Bekkerman, R., McCallum, A., Huang, G.: Automatic categorization of email into folders. benchmark experiments on enron and sri corpora. In: Bekkerman, R., McCallum, A., Huang, G. (eds.) Technical Report IR-418, Centre for Intelligent Information Retrieval, UMASS (2004)"},{"key":"24_CR4","doi-asserted-by":"crossref","unstructured":"Biber, D.: Representativeness in Corpus Design. Literary and Linguistic Computing\u00a08(4), 243\u2013257 (1993)","DOI":"10.1093\/llc\/8.4.243"},{"key":"24_CR5","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511519871","volume-title":"Dimensions of Register Variation:a Cross-Linguistic Comparison","author":"D. Biber","year":"1995","unstructured":"Biber, D.: Dimensions of Register Variation:a Cross-Linguistic Comparison. Cambridge University Press, New York (1995)"},{"key":"24_CR6","unstructured":"Boese, E.S.: Stereotyping the web: genre classification of web documents. Master\u2019s thesis, Colorado State University (2005)"},{"key":"24_CR7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L. Breiman","year":"2001","unstructured":"Breiman, L.: Random forests. Machine Learning\u00a045, 5\u201332 (2001)","journal-title":"Machine Learning"},{"key":"24_CR8","unstructured":"Chao, C., Liaw, A., Breiman, L.: Using random forest to learn imbalanced data (2004), http:\/\/www.stat.berkeley.edu\/~breiman\/RandomForests\/"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Curran, J., Clark, S.: Investigating GIS and Smoothing for Maximum Entropy Taggers. In: Proceedings Aunnual Meeting European Chapter of the Assoc. of Computational Linguistics, pp. 91\u201398 (2003)","DOI":"10.3115\/1067807.1067821"},{"issue":"11","key":"24_CR10","doi-asserted-by":"publisher","first-page":"1506","DOI":"10.1002\/asi.20427","volume":"57","author":"A. Finn","year":"2006","unstructured":"Finn, A., Kushmerick, N.: Learning to classify documents according to genre. Journal of American Society for Information Science and Technology\u00a057(11), 1506\u20131518 (2006)","journal-title":"Journal of American Society for Information Science and Technology"},{"key":"24_CR11","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1145\/336597.336639","volume-title":"Proceedings 5th ACM Intl. Conf. Digital Libraries","author":"G. Giuffrida","year":"2000","unstructured":"Giuffrida, G., Shek, E., Yang, J.: Knowledge-based metadata extraction from postscript file. In: Proceedings 5th ACM Intl. Conf. Digital Libraries, pp. 77\u201384. ACM Press, New York (2000)"},{"key":"24_CR12","doi-asserted-by":"crossref","unstructured":"Han, H., Giles, L., Manavoglu, E., Zha, H., Zhang, Z., Fox, E.A.: Automatic document metadata extraction using support vector machines. In: 3rd ACM\/IEEECS Conf. Digital Libraries, pp. 37\u201348 (2003)","DOI":"10.1109\/JCDL.2003.1204842"},{"key":"24_CR13","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.3115\/991250.991324","volume":"2","author":"J. Karlgren","year":"1994","unstructured":"Karlgren, J., Cutting, D.: Recognizing text genres with simple metric using discriminant analysis. Proceedings 15th Conf. Comp. Ling.\u00a02, 1071\u20131075 (1994)","journal-title":"Proceedings 15th Conf. Comp. Ling."},{"key":"24_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"460","DOI":"10.1007\/11735106_41","volume-title":"ECIR 2006.","author":"S.W. Ke","year":"2006","unstructured":"Ke, S.W., Bowerman, C.: Perc: A personal email classifier. In: Lalmas, M., MacFarlane, A., R\u00fcger, S., Tombros, A., Tsikrika, T., Yavlinsky, A. (eds.) ECIR 2006. LNCS, vol.\u00a03936, pp. 460\u2013463. Springer, Heidelberg (2006)"},{"key":"24_CR15","doi-asserted-by":"crossref","unstructured":"Kessler, G., Nunberg, B., Schuetze, H.: Automatic detection of text genre. In: Proceedings 35th Ann., pp. 32\u201338 (1997)","DOI":"10.3115\/976909.979622"},{"key":"24_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/11863878_6","volume-title":"Research and Advanced Technology for Digital Libraries","author":"Y. Kim","year":"2006","unstructured":"Kim, Y., Ross, S.: Genre classification in automated ingest and appraisal metadata. In: Gonzalo, J., Thanos, C., Verdejo, M.F., Carrasco, R.C. (eds.) ECDL 2006. LNCS, vol.\u00a04172, pp. 63\u201374. Springer, Heidelberg (2006)"},{"key":"24_CR17","unstructured":"Kim, Y., Webber, B.: Implicit reference to citations: A study of astronomy papers. Presentation at the 20th CODATA international Conference, Beijing, China. (2006), http:\/\/eprints.erpanet.org\/paperid115"},{"key":"24_CR18","doi-asserted-by":"publisher","first-page":"172","DOI":"10.2481\/dsj.6.S172","volume":"6","author":"Y. Kim","year":"2007","unstructured":"Kim, Y., Ross, S.: Detecting family resemblance: Automated genre classification. Data Science\u00a06, S172\u2013S183 (2007), http:\/\/www.jstage.jst.go.jp\/article\/dsj\/6\/0\/s172\/_pdf","journal-title":"Data Science"},{"key":"24_CR19","doi-asserted-by":"crossref","unstructured":"Kim, Y., Ross, S.: The Naming of Cats: Automated genre classification. International Journal for Digital Curation\u00a02(1) (2007), http:\/\/www.ijdc.net\/.\/ijdc\/article\/view\/24","DOI":"10.2218\/ijdc.v2i1.13"},{"issue":"2","key":"24_CR20","first-page":"313","volume":"19","author":"M.P. Marcus","year":"1994","unstructured":"Marcus, M.P., Santorini, B., Mareinkiewicz, M.A.: Building a large annotated corpus of English: the Penn Treebank. Computational Linguistics\u00a019(2), 313\u2013330 (1994)","journal-title":"Computational Linguistics"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Rauber, A., M\u00fcller-K\u00f6gler, A.: Integrating automatic genre analysis into digital libraries. In: Proceedings ACM\/IEEE Joint Conf. Digital Libraries, Roanoke, VA, pp. 1\u201310 (2001)","DOI":"10.1145\/379437.379439"},{"key":"24_CR22","doi-asserted-by":"crossref","unstructured":"Ross, S., Hedstrom, M.: Preservation research and sustainable digital libraries. International Journal of Digital Libraries, (2005) DOI: 10.1007\/s00799-004-0099-3","DOI":"10.1007\/s00799-004-0099-3"},{"key":"24_CR23","unstructured":"Thoma, G.: Automating the production of bibliographic records. Technical report, Lister Hill National Center for Biomedical Communication, US National Library of Medicine (2001)"},{"key":"24_CR24","volume-title":"Data mining: Practical machine learning tools and techniques","author":"H.I. Witten","year":"2005","unstructured":"Witten, H.I., Frank, E.: Data mining: Practical machine learning tools and techniques. Morgan Kaufmann, San Francisco (2005)"}],"container-title":["Lecture Notes in Computer Science","Digital Libraries: Research and Development"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77088-6_24.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,28]],"date-time":"2021-08-28T18:41:39Z","timestamp":1630176099000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77088-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540770879"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77088-6_24","relation":{},"subject":[]}}