{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T07:14:28Z","timestamp":1784099668291,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,4,20]],"date-time":"2009-04-20T00:00:00Z","timestamp":1240185600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,4,20]]},"DOI":"10.1145\/1526709.1526721","type":"proceedings-article","created":{"date-parts":[[2009,4,21]],"date-time":"2009-04-21T14:17:17Z","timestamp":1240323437000},"page":"81-90","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Efficient overlap and content reuse detection in blogs and online news articles"],"prefix":"10.1145","author":[{"given":"Jong Wook","family":"Kim","sequence":"first","affiliation":[{"name":"Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"K. Sel\u00e7uk","family":"Candan","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junichi","family":"Tatemura","sequence":"additional","affiliation":[{"name":"NEC Labs, America, Cupertino, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2009,4,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"David Sifry's Blog. http:\/\/www.sifry.com\/alerts\/.  David Sifry's Blog. http:\/\/www.sifry.com\/alerts\/."},{"key":"e_1_3_2_1_2_1","unstructured":"Google Blog Search. http:\/\/blogsearch.google.com blogsearch.  Google Blog Search. http:\/\/blogsearch.google.com blogsearch."},{"key":"e_1_3_2_1_3_1","author":"Google","unstructured":"Google News. http:\/\/news.google.com. Google News. http:\/\/news.google.com.","journal-title":"News. http:\/\/news.google.com."},{"key":"e_1_3_2_1_4_1","unstructured":"Google Book Search. http:\/\/books.google.com\/.  Google Book Search. http:\/\/books.google.com\/."},{"key":"e_1_3_2_1_5_1","author":"Yahoo","unstructured":"Yahoo News. http:\/\/news.yahoo.com. Yahoo News. http:\/\/news.yahoo.com.","journal-title":"News. http:\/\/news.yahoo.com."},{"key":"e_1_3_2_1_6_1","unstructured":"The MD5 Message-Digest Algorithm. http:\/\/tools.ietf.org\/html\/rfc1321.  The MD5 Message-Digest Algorithm. http:\/\/tools.ietf.org\/html\/rfc1321."},{"key":"e_1_3_2_1_7_1","volume-title":"Aggregation, Analysis and Dynamics","author":"Weblogging Ecosystem Workshop","year":"2006","unstructured":"WWW'06 Workshop on the Weblogging Ecosystem : Aggregation, Analysis and Dynamics . 2006 . WWW'06 Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics. 2006."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/WI.2005.151"},{"key":"e_1_3_2_1_9_1","volume-title":"VLDB","author":"Arasu A.","year":"2006","unstructured":"A. Arasu , V. Ganti , and R. Kaushik . Efficient exact set-similarity joins . In VLDB , 2006 . A. Arasu, V. Ganti, and R. Kaushik. Efficient exact set-similarity joins. In VLDB, 2006."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242591"},{"key":"e_1_3_2_1_11_1","volume-title":"VLDB","author":"Berchtold S.","year":"1996","unstructured":"S. Berchtold , D.A. Keim , and H. Kriegei . The X-tree: An Index Structure for High--Dimensional Data . In VLDB , 1996 . S. Berchtold, D.A. Keim, and H. Kriegei. The X-tree: An Index Structure for High--Dimensional Data. In VLDB, 1996."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30213-1_6"},{"key":"e_1_3_2_1_13_1","volume-title":"The Weblog Handbook: Practical Advice on Creating and Maintaining Your Blog","author":"Blood R.","year":"2002","unstructured":"R. Blood . The Weblog Handbook: Practical Advice on Creating and Maintaining Your Blog . Perseus Books Group , 2002 . R. Blood. The Weblog Handbook: Practical Advice on Creating and Maintaining Your Blog. Perseus Books Group, 2002."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of Compression and Complexity of Sequences","author":"Broder A.Z.","year":"1997","unstructured":"A.Z. Broder . On the resemblance and containment of documents . In Proceedings of Compression and Complexity of Sequences , 1997 . A.Z. Broder. On the resemblance and containment of documents. In Proceedings of Compression and Complexity of Sequences, 1997."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/223784.223855"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.1999.754960"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2006.9"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2004.830793"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281213"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.844059"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/506309.506311"},{"key":"e_1_3_2_1_22_1","volume-title":"VLDB","author":"Gionis A.","year":"1999","unstructured":"A. Gionis , P. Indyk , and R. Motwani . Similarity Search in High Dimensions via Hashing . In VLDB , 1999 . A. Gionis, P. Indyk, and R. Motwani. Similarity Search in High Dimensions via Hashing. In VLDB, 1999."},{"key":"e_1_3_2_1_23_1","volume-title":"VLDB","author":"Gravano L.","year":"2001","unstructured":"L. Gravano , P.G. Ipeirotis , H.V. Jagadish , N. Koudas , S. Muthukrishnan , and D. Srivastava Approximate String Joins in a Database (Almost) for Free . In VLDB , 2001 . L. Gravano, P.G. Ipeirotis, H.V. Jagadish, N.Koudas, S. Muthukrishnan, and D. Srivastava Approximate String Joins in a Database (Almost) for Free. In VLDB, 2001."},{"key":"e_1_3_2_1_24_1","volume-title":"USENIX Workshop on Electronic Commerce","author":"Heintze N.","year":"1996","unstructured":"N. Heintze . Scalable document fingerprinting . In USENIX Workshop on Electronic Commerce , 1996 . N. Heintze. Scalable document fingerprinting. In USENIX Workshop on Electronic Commerce, 1996."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of Uncertainty in Artificial Intelligence","author":"Hofmann T.","year":"1999","unstructured":"T. Hofmann . Probabilistic latent semantic analysis . In Proceedings of Uncertainty in Artificial Intelligence , 1999 . T. Hofmann. Probabilistic latent semantic analysis. In Proceedings of Uncertainty in Artificial Intelligence, 1999."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/258533.258656"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/253260.253347"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2007.19"},{"key":"e_1_3_2_1_29_1","unstructured":"J.W. Kim K.S. Candan and J.Tatemura. Organization and Tagging of Blog Entries based on Content Reuse. submitted.  J.W. Kim K.S. Candan and J.Tatemura. Organization and Tagging of Blog Entries based on Content Reuse. submitted."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1379092.1379117"},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of the USENIX","author":"Manber U.","year":"1994","unstructured":"U. Manber . Finding Similar Files in a Large File System . In Proceedings of the USENIX Winter 1994 Technical Conference , 1994. U. Manber. Finding Similar Files in a Large File System. In Proceedings of the USENIX Winter 1994 Technical Conference, 1994."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242592"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1099554.1099695"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/872757.872770"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1007568.1007652"},{"key":"e_1_3_2_1_36_1","volume-title":"SCAM: A Copy Detection Mechanism for Digital Documents. Second Annual Conference on the Theory and Practice of Digital Libraries","author":"Shivakumar N.","year":"1995","unstructured":"N. Shivakumar and H. Garcia-Molina . SCAM: A Copy Detection Mechanism for Digital Documents. Second Annual Conference on the Theory and Practice of Digital Libraries , 1995 . N. Shivakumar and H. Garcia-Molina. SCAM: A Copy Detection Mechanism for Digital Documents. Second Annual Conference on the Theory and Practice of Digital Libraries, 1995."},{"key":"e_1_3_2_1_37_1","volume-title":"International Workshop on the World Wide Web and Databases","author":"Shrivakumar N.","year":"1998","unstructured":"N. Shrivakumar and H. Garcia-Molina Finding near-replicas of documents on the Web . In International Workshop on the World Wide Web and Databases , 1998 . N. Shrivakumar and H. Garcia-Molina Finding near-replicas of documents on the Web. In International Workshop on the World Wide Web and Databases, 1998."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148243"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/296854.277632"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/1367497.1367516"}],"event":{"name":"WWW '09: The 18th International World Wide Web Conference","location":"Madrid Spain","acronym":"WWW '09","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","ACM Association for Computing Machinery"]},"container-title":["Proceedings of the 18th international conference on World wide web"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526721","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1526709.1526721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T13:30:29Z","timestamp":1750253429000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1526709.1526721"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,4,20]]},"references-count":40,"alternative-id":["10.1145\/1526709.1526721","10.1145\/1526709"],"URL":"https:\/\/doi.org\/10.1145\/1526709.1526721","relation":{},"subject":[],"published":{"date-parts":[[2009,4,20]]},"assertion":[{"value":"2009-04-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}