{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:23:37Z","timestamp":1750220617434,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000208","name":"Institute of Museum and Library Services","doi-asserted-by":"publisher","award":["LG-71-17-0202-17"],"award-info":[{"award-number":["LG-71-17-0202-17"]}],"id":[{"id":"10.13039\/100000208","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,8]]},"DOI":"10.1145\/3383583.3398540","type":"proceedings-article","created":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T04:18:32Z","timestamp":1596255512000},"page":"167-176","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Identifying Documents In-Scope of a Collection from Web Archives"],"prefix":"10.1145","author":[{"given":"Krutarth","family":"Patel","sequence":"first","affiliation":[{"name":"Kansas State University, Manhattan, KS, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cornelia","family":"Caragea","sequence":"additional","affiliation":[{"name":"University of Illinois at Chicago, Chicago, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark E.","family":"Phillips","sequence":"additional","affiliation":[{"name":"University of North Texas, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathaniel T.","family":"Fox","sequence":"additional","affiliation":[{"name":"University of North Texas, New York, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,8]]},"reference":[{"volume-title":"Fateh ud din B Mehmood, and Michael L Nelson","year":"2015","author":"Alam Sawood","key":"e_1_3_2_2_1_1"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-016-0184-4"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Yasmin AlNoamany Michele C Weigle and Michael L Nelson. 2017. Generating Stories From Archived Collections. In WebSci'17. ACM 309--318.  Yasmin AlNoamany Michele C Weigle and Michael L Nelson. 2017. Generating Stories From Archived Collections. In WebSci'17. ACM 309--318.","DOI":"10.1145\/3091478.3091508"},{"key":"e_1_3_2_2_4_1","unstructured":"Archive-It. 2017. Archive-It Homepage. https:\/\/archive-it.org\/.  Archive-It. 2017. Archive-It Homepage. https:\/\/archive-it.org\/."},{"volume-title":"Archive Assisted Archival Fixity Verification Framework","author":"Aturban Mohamed","key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","DOI":"10.1109\/JCDL.2019.00032"},{"key":"e_1_3_2_2_6_1","unstructured":"Jefferson Bailey. 2017. https:\/\/twitter.com\/jefferson_bail\/status\/867808876917178368.  Jefferson Bailey. 2017. https:\/\/twitter.com\/jefferson_bail\/status\/867808876917178368."},{"key":"e_1_3_2_2_7_1","volume-title":"JMLR","volume":"3","author":"Bengio Yoshua","year":"2003"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"volume-title":"Proceedings of the SARA.","year":"2011","author":"Caragea Cornelia","key":"e_1_3_2_2_9_1"},{"volume-title":"Sujatha Das Gollapalli, and C Lee Giles","year":"2016","author":"Caragea Cornelia","key":"e_1_3_2_2_10_1"},{"volume-title":"A learner-independent evaluation of the usefulness of statistical phrases for automated text categorization. Text databases and document management: Theory and practice","year":"2001","author":"Caropreso Maria Fernanda","key":"e_1_3_2_2_11_1"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078186"},{"key":"e_1_3_2_2_14_1","unstructured":"International Internet Preservation Consortium. 2017. Members. http:\/\/netpreserve.org\/about-us\/members.  International Internet Preservation Consortium. 2017. Members. http:\/\/netpreserve.org\/about-us\/members."},{"key":"e_1_3_2_2_15_1","volume-title":"ISMB","volume":"1999","author":"Craven Mark","year":"1999"},{"volume-title":"The Library of Congress Web Archives: Dipping a Toe in a Lake of Data. https:\/\/blogs.loc.gov\/thesignal\/2019\/01\/the-library-of-congress-web-archives-dipping-a-toe-in-a-lake-of-data\/.","year":"2019","author":"Dooley Chase","key":"e_1_3_2_2_16_1"},{"volume-title":"Inductive Learning Algorithms and Representations for Text Categorization. In CIKM '98","year":"1998","author":"Dumais Susan","key":"e_1_3_2_2_17_1"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/944919.944974"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.5555\/3176748.3176757"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-53914-5_45"},{"key":"e_1_3_2_2_21_1","unstructured":"HathiTrust. [n. d.]. HathiTrust Statistics Information. (https:\/\/www.hathitrust.org\/statistics_info.  HathiTrust. [n. d.]. HathiTrust Statistics Information. (https:\/\/www.hathitrust.org\/statistics_info."},{"volume-title":"Proc. of the 10th ECML. 137--142","year":"1998","author":"Joachims Thorsten","key":"e_1_3_2_2_23_1"},{"volume-title":"Effective use of word order for text categorization with convolutional neural networks. arXiv preprint arXiv:1412.1058","year":"2014","author":"Johnson Rie","key":"e_1_3_2_2_24_1"},{"volume-title":"A convolutional neural network for modelling sentences. arXiv preprint arXiv:1404.2188","year":"2014","author":"Kalchbrenner Nal","key":"e_1_3_2_2_25_1"},{"volume-title":"Convolutional neural networks for sentence classification. arXiv preprint arXiv:1408.5882","year":"2014","author":"Kim Yoon","key":"e_1_3_2_2_26_1"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"crossref","unstructured":"Ajith Kodakateri Pudhiyaveetil Susan Gauch Hiep Luong and Josh Eno. 2009. Conceptual recommender system for CiteSeerX. In RecSys. ACM 241--244.  Ajith Kodakateri Pudhiyaveetil Susan Gauch Hiep Luong and Josh Eno. 2009. Conceptual recommender system for CiteSeerX. In RecSys. ACM 241--244.","DOI":"10.1145\/1639714.1639758"},{"volume-title":"International Conference on Machine Learning. 1188--1196","year":"2014","author":"Le Quoc","key":"e_1_3_2_2_28_1"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"volume-title":"Proceedings of the Twentieth International Conference (ICML 2003","year":"2003","author":"Lu Qing","key":"e_1_3_2_2_30_1"},{"key":"e_1_3_2_2_31_1","unstructured":"Qing Lu and Lise Getoor. 2003 b. Link-based Classification. In ICML.  Qing Lu and Lise Getoor. 2003 b. Link-based Classification. In ICML."},{"volume-title":"Introduction to Information Retrieval","author":"Manning Christopher D.","key":"e_1_3_2_2_32_1"},{"volume-title":"AAAI-98 Workshop on Learning for Text Categorization.","year":"1998","author":"McCallum Andrew","key":"e_1_3_2_2_33_1"},{"volume-title":"AAAI-98 Workshop on Learning for Text Categorization.","year":"1998","author":"McCallum Andrew","key":"e_1_3_2_2_34_1"},{"key":"e_1_3_2_2_35_1","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119.  Tomas Mikolov Ilya Sutskever Kai Chen Greg S Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems. 3111--3119."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209542.3209560"},{"key":"e_1_3_2_2_37_1","volume-title":"Archiving Conference","volume":"2013","author":"Phillips Mark","year":"2013"},{"volume-title":"Induction of decision trees. Machine learning","year":"1986","author":"Quinlan J. Ross","key":"e_1_3_2_2_38_1"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"volume-title":"Multichannel variable-size convolution for sentence classification. arXiv preprint arXiv:1603.04513","year":"2016","author":"Yin Wenpeng","key":"e_1_3_2_2_40_1"},{"key":"e_1_3_2_2_41_1","unstructured":"Xiang Zhang Junbo Zhao and Yann LeCun. 2015. Character-level convolutional networks for text classification. In Advances in neural information processing systems. 649--657.  Xiang Zhang Junbo Zhao and Yann LeCun. 2015. Character-level convolutional networks for text classification. In Advances in neural information processing systems. 649--657."},{"key":"e_1_3_2_2_42_1","unstructured":"Tong Zhou Yi Zhang and Jianguo Lu. 2016. Classifying computer science papers. In IJCAI.  Tong Zhou Yi Zhang and Jianguo Lu. 2016. Classifying computer science papers. In IJCAI."}],"event":{"name":"JCDL '20: The ACM\/IEEE Joint Conference on Digital Libraries in 2020","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","SIGIR ACM Special Interest Group on Information Retrieval","IEEE Institute of Electrical and Electronics Engineers"],"location":"Virtual Event China","acronym":"JCDL '20"},"container-title":["Proceedings of the ACM\/IEEE Joint Conference on Digital Libraries in 2020"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383583.3398540","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3383583.3398540","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:11Z","timestamp":1750197671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3383583.3398540"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":41,"alternative-id":["10.1145\/3383583.3398540","10.1145\/3383583"],"URL":"https:\/\/doi.org\/10.1145\/3383583.3398540","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]},"assertion":[{"value":"2020-08-01","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}