{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:27:24Z","timestamp":1750307244685,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,3,26]],"date-time":"2012-03-26T00:00:00Z","timestamp":1332720000000},"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":[[2012,3,26]]},"DOI":"10.1145\/2245276.2245408","type":"proceedings-article","created":{"date-parts":[[2012,6,11]],"date-time":"2012-06-11T13:03:31Z","timestamp":1339419811000},"page":"696-701","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["RetriBlog"],"prefix":"10.1145","author":[{"given":"Rafael","family":"Ferreira","sequence":"first","affiliation":[{"name":"Federal University of Pernambuco, Recife, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rinaldo","family":"Lima","sequence":"additional","affiliation":[{"name":"Federal, University of Pernambuco, Recife, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean","family":"Melo","sequence":"additional","affiliation":[{"name":"Federal University of Alagoas, Macei\u00f3, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evandro","family":"Costa","sequence":"additional","affiliation":[{"name":"Federal University of Alagoas, Macei\u00f3, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fred","family":"Freitas","sequence":"additional","affiliation":[{"name":"Federal University of Pernambuco, Recife, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrique","family":"Pacca","sequence":"additional","affiliation":[{"name":"Federal University of Alagoas, Macei\u00f3, Brazil"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,3,26]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Modern Information Retrieval","author":"Baeza-Yates R.","year":"1999","unstructured":"R. Baeza-Yates and B. Ribeiro-Neto . Modern Information Retrieval . Addison Wesley , 1 st edition, May 1999 . R. Baeza-Yates and B. Ribeiro-Neto. Modern Information Retrieval. Addison Wesley, 1st edition, May 1999.","edition":"1"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/MITP.2009.1"},{"key":"e_1_3_2_1_3_1","volume-title":"Information Retrieval: Data Structures and Algorithms","author":"Frakes W. B.","year":"1992","unstructured":"W. B. Frakes and R. Baeza-Yates . Information Retrieval: Data Structures and Algorithms . Prentice Hall PTR , June 1992 . W. B. Frakes and R. Baeza-Yates. Information Retrieval: Data Structures and Algorithms. Prentice Hall PTR, June 1992."},{"key":"e_1_3_2_1_4_1","volume-title":"3rd Annual Workshop on the Weblogging Ecosystem","author":"Fujimura K.","year":"2006","unstructured":"K. Fujimura , H. Toda , T. Inoue , N. Hiroshima , R. Kataoka , and M. Sugizaki . Blogranger - a multi-faceted blog search engine . In 3rd Annual Workshop on the Weblogging Ecosystem , 2006 . K. Fujimura, H. Toda, T. Inoue, N. Hiroshima, R. Kataoka, and M. Sugizaki. Blogranger - a multi-faceted blog search engine. In 3rd Annual Workshop on the Weblogging Ecosystem, 2006."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/0165551506062337"},{"key":"e_1_3_2_1_6_1","first-page":"123","volume-title":"Proceedings of the 2nd International Conference on Internet Technologies and Applications","author":"Gottron T.","year":"2007","unstructured":"T. Gottron . Evaluating content extraction on html documents . Proceedings of the 2nd International Conference on Internet Technologies and Applications , pages 123 -- 132 , 2007 . T. Gottron. Evaluating content extraction on html documents. Proceedings of the 2nd International Conference on Internet Technologies and Applications, pages 123--132, 2007."},{"key":"e_1_3_2_1_7_1","volume-title":"Manning Publications","author":"Hatcher E.","year":"2004","unstructured":"E. Hatcher and O. Gospodnetic . Lucene in Action (In Action series) . Manning Publications , December 2004 . E. Hatcher and O. Gospodnetic. Lucene in Action (In Action series). Manning Publications, December 2004."},{"key":"e_1_3_2_1_8_1","volume-title":"May","author":"Hotho A.","year":"2005","unstructured":"A. Hotho , A. N\u00fcrnberger , and G. Paa\u00df . A brief survey of text mining. LDV Forum - GLDV Journal for Computational Linguistics and Language Technology, 20(1): 19--62 , May 2005 . A. Hotho, A. N\u00fcrnberger, and G. Paa\u00df. A brief survey of text mining. LDV Forum - GLDV Journal for Computational Linguistics and Language Technology, 20(1): 19--62, May 2005."},{"key":"e_1_3_2_1_9_1","volume-title":"In: Proc. of the International Conf. on Management of Data COMAD","author":"Joshi M.","year":"2006","unstructured":"M. Joshi . Blogharvest : Blog mining and search framework . In In: Proc. of the International Conf. on Management of Data COMAD , 2006 . M. Joshi. Blogharvest: Blog mining and search framework. In In: Proc. of the International Conf. on Management of Data COMAD, 2006."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1718487.1718542"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 20th international conference on computer processing of oriental languages","author":"Li Baoli Y. S.","year":"2003","unstructured":"Y. S. Li Baoli and L. Qin . An improved k-nearest neighbor algorithm for text categorization . Proceedings of the 20th international conference on computer processing of oriental languages , 2003 . Y. S. Li Baoli and L. Qin. An improved k-nearest neighbor algorithm for text categorization. Proceedings of the 20th international conference on computer processing of oriental languages, 2003."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to Information Retrieval","author":"Manning C. D.","year":"2008","unstructured":"C. D. Manning , P. Raghavan , and H. Sch\u00fctze . Introduction to Information Retrieval . Cambridge University Press , 1 edition, July 2008 . C. D. Manning, P. Raghavan, and H. Sch\u00fctze. Introduction to Information Retrieval. Cambridge University Press, 1 edition, July 2008."},{"key":"e_1_3_2_1_13_1","volume-title":"Computer science, String (computer science), String metric, Damerau? Levenshtein distance, Spell checker, Hamming distance","author":"Miller F. P.","year":"2009","unstructured":"F. P. Miller , A. F. Vandome , and J. McBrewster. Levenshtein Distance: Information theory , Computer science, String (computer science), String metric, Damerau? Levenshtein distance, Spell checker, Hamming distance . Alpha Press , 2009 . F. P. Miller, A. F. Vandome, and J. McBrewster. Levenshtein Distance: Information theory, Computer science, String (computer science), String metric, Damerau? Levenshtein distance, Spell checker, Hamming distance. Alpha Press, 2009."},{"key":"e_1_3_2_1_14_1","volume-title":"Maching Learning","author":"Mitchell T.","year":"1997","unstructured":"T. Mitchell . Maching Learning . McGraw-Hill education, 1997 . T. Mitchell. Maching Learning. McGraw-Hill education, 1997."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/544220.544228"},{"key":"e_1_3_2_1_16_1","unstructured":"M. F. Porter. An algorithm for suffix stripping. pages 313--316 1997.   M. F. Porter. An algorithm for suffix stripping. pages 313--316 1997."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1083-6101.2007.00380.x"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/505282.505283"},{"volume-title":"State of the blogosphere","year":"2008","key":"e_1_3_2_1_19_1","unstructured":"Technorati. State of the blogosphere 2008 . http:\/\/technorati.com\/blogging\/feature\/state-of-the-blogosphere-2008\/, 2008. Accessed on March 2011. Technorati. State of the blogosphere 2008. http:\/\/technorati.com\/blogging\/feature\/state-of-the-blogosphere-2008\/, 2008. Accessed on March 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/DEXA.2008.12"}],"event":{"name":"SAC 2012: ACM Symposium on Applied Computing","sponsor":["SIGAPP ACM Special Interest Group on Applied Computing"],"location":"Trento Italy","acronym":"SAC 2012"},"container-title":["Proceedings of the 27th Annual ACM Symposium on Applied Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2245276.2245408","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2245276.2245408","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:52:02Z","timestamp":1750243922000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2245276.2245408"}},"subtitle":["a framework for creating blog crawlers"],"short-title":[],"issued":{"date-parts":[[2012,3,26]]},"references-count":20,"alternative-id":["10.1145\/2245276.2245408","10.1145\/2245276"],"URL":"https:\/\/doi.org\/10.1145\/2245276.2245408","relation":{},"subject":[],"published":{"date-parts":[[2012,3,26]]},"assertion":[{"value":"2012-03-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}