{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:26:37Z","timestamp":1750307197851,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2010,1,14]],"date-time":"2010-01-14T00:00:00Z","timestamp":1263427200000},"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":[[2010,1,14]]},"DOI":"10.1145\/2108616.2108661","type":"proceedings-article","created":{"date-parts":[[2012,1,24]],"date-time":"2012-01-24T16:47:19Z","timestamp":1327423639000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Detecting splogs using similarities of splog HTML structures"],"prefix":"10.1145","author":[{"given":"Taichi","family":"Katayama","sequence":"first","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takayuki","family":"Yoshinaka","sequence":"additional","affiliation":[{"name":"Tokyo Denki University, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takehito","family":"Utsuro","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuhide","family":"Kawada","sequence":"additional","affiliation":[{"name":"Navix Co., Ltd., Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Fukuhara","sequence":"additional","affiliation":[{"name":"University of Tokyo, Kashiwa, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2010,1,14]]},"reference":[{"unstructured":"Wikipedia Spam blog. http:\/\/en.wikipedia.org\/wiki\/Spam_blog. Wikipedia Spam blog . http:\/\/en.wikipedia.org\/wiki\/Spam_blog.","key":"e_1_3_2_1_1_1"},{"unstructured":"Wikipedia Ping (blogging). http:\/\/en.wikipedia.org\/wiki\/Ping_(blogging). Wikipedia Ping (blogging) . http:\/\/en.wikipedia.org\/wiki\/Ping_(blogging).","key":"e_1_3_2_1_2_1"},{"key":"e_1_3_2_1_3_1","first-page":"479","volume-title":"Proc. 8th IEEE CIT","author":"Bing L.","year":"2008","unstructured":"L. Bing , Y. Wang , Y. Zhang , and H. Wang . Primary content extraction with mountain model . In Proc. 8th IEEE CIT , pages 479 -- 484 , 2008 . L. Bing, Y. Wang, Y. Zhang, and H. Wang. Primary content extraction with mountain model. In Proc. 8th IEEE CIT, pages 479--484, 2008."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_4_1","DOI":"10.1109\/TKDE.2005.138"},{"key":"e_1_3_2_1_5_1","volume-title":"WWW 2004 Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics","author":"Glance N.","year":"2004","unstructured":"N. Glance , M. Hurst , and T. Tomokiyo . Blogpulse: Automated trend discovery for Weblogs . In WWW 2004 Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics , 2004 . N. Glance, M. Hurst, and T. Tomokiyo. Blogpulse: Automated trend discovery for Weblogs. In WWW 2004 Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics, 2004."},{"key":"e_1_3_2_1_6_1","first-page":"39","volume-title":"Proc. 1st AIRWeb","author":"Gy\u00f6ngyi Z.","year":"2005","unstructured":"Z. Gy\u00f6ngyi and H. Garcia-Molina . Web spam taxonomy . In Proc. 1st AIRWeb , pages 39 -- 47 , 2005 . Z. Gy\u00f6ngyi and H. Garcia-Molina. Web spam taxonomy. In Proc. 1st AIRWeb, pages 39--47, 2005."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1145\/1531914.1531921"},{"key":"e_1_3_2_1_8_1","first-page":"92","volume-title":"Proc. 2006 AAAI Spring Symp. Computational Approaches to Analyzing Weblogs","author":"Kolari P.","year":"2006","unstructured":"P. Kolari , T. Finin , and A. Joshi . SVMs for the Blogosphere: Blog identification and Splog detection . In Proc. 2006 AAAI Spring Symp. Computational Approaches to Analyzing Weblogs , pages 92 -- 99 , 2006 . P. Kolari, T. Finin, and A. Joshi. SVMs for the Blogosphere: Blog identification and Splog detection. In Proc. 2006 AAAI Spring Symp. Computational Approaches to Analyzing Weblogs, pages 92--99, 2006."},{"key":"e_1_3_2_1_9_1","volume-title":"Tutorial at ICWSM","author":"Kolari P.","year":"2007","unstructured":"P. Kolari , T. Finin , and A. Joshi . Spam in blogs and social media . In Tutorial at ICWSM , 2007 . P. Kolari, T. Finin, and A. Joshi. Spam in blogs and social media. In Tutorial at ICWSM, 2007."},{"key":"e_1_3_2_1_10_1","volume-title":"Proc. 3rd Ann. Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics","author":"Kolari P.","year":"2006","unstructured":"P. Kolari , A. Joshi , and T. Finin . Characterizing the splogosphere . In Proc. 3rd Ann. Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics , 2006 . P. Kolari, A. Joshi, and T. Finin. Characterizing the splogosphere. In Proc. 3rd Ann. Workshop on the Weblogging Ecosystem: Aggregation, Analysis and Dynamics, 2006."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_11_1","DOI":"10.5555\/188490.188495"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1145\/775047.775134"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.1145\/1244408.1244410"},{"key":"e_1_3_2_1_15_1","volume-title":"Proc. 1st AIRWeb","author":"Mishne G.","year":"2005","unstructured":"G. Mishne , D. Carmel , and R. Lempel . Blocking blog spam with language model disagreement . In Proc. 1st AIRWeb , 2005 . G. Mishne, D. Carmel, and R. Lempel. Blocking blog spam with language model disagreement. In Proc. 1st AIRWeb, 2005."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_16_1","DOI":"10.1145\/1013367.1013455"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_17_1","DOI":"10.1145\/1451983.1451993"},{"key":"e_1_3_2_1_18_1","first-page":"839","volume-title":"Proc. 17th ICML","author":"Schohn G.","year":"2000","unstructured":"G. Schohn and D. Cohn . Less is more: Active learning with support vector machines . In Proc. 17th ICML , pages 839 -- 846 , 2000 . G. Schohn and D. Cohn. Less is more: Active learning with support vector machines. In Proc. 17th ICML, pages 839--846, 2000."},{"key":"e_1_3_2_1_19_1","first-page":"999","volume-title":"Proc. 17th ICML","author":"Tong S.","year":"2000","unstructured":"S. Tong and D. Koller . Support vector machine active learning with applications to text classification . In Proc. 17th ICML , pages 999 -- 1006 , 2000 . S. Tong and D. Koller. Support vector machine active learning with applications to text classification. In Proc. 17th ICML, pages 999--1006, 2000."},{"key":"e_1_3_2_1_20_1","first-page":"25","volume-title":"Proc. 2nd AIRWeb","author":"Urvoy T.","year":"2006","unstructured":"T. Urvoy , T. Lavergne , and P. Filoche . Tracking Web spam with hidden style similarity . In Proc. 2nd AIRWeb , pages 25 -- 30 , 2006 . T. Urvoy, T. Lavergne, and P. Filoche. Tracking Web spam with hidden style similarity. In Proc. 2nd AIRWeb, pages 25--30, 2006."},{"key":"e_1_3_2_1_21_1","volume-title":"Statistical Learning Theory","author":"Vapnik V. N.","year":"1998","unstructured":"V. N. Vapnik . Statistical Learning Theory . Wiley-Interscience , 1998 . V. N. Vapnik. Statistical Learning Theory. Wiley-Interscience, 1998."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_22_1","DOI":"10.1145\/1242572.1242612"},{"issue":"1","key":"e_1_3_2_1_23_1","first-page":"29","article-title":"Primary content extraction from news pages without training data","volume":"8","author":"Yoshida M.","year":"2009","unstructured":"M. Yoshida and M. Yamamoto . Primary content extraction from news pages without training data . DBSJ Journal , 8 ( 1 ): 29 -- 34 , 2009 . (in Japanese). M. Yoshida and M. Yamamoto. Primary content extraction from news pages without training data. DBSJ Journal, 8(1):29--34, 2009. (in Japanese).","journal-title":"DBSJ Journal"}],"event":{"sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"],"acronym":"ICUIMC '10","name":"ICUIMC '10: The 4th International Conference on Ubiquitous Information Management and Communication","location":"Suwon Republic of Korea"},"container-title":["Proceedings of the 4th International Conference on Uniquitous Information Management and Communication"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2108616.2108661","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2108616.2108661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T10:06:09Z","timestamp":1750241169000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2108616.2108661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,1,14]]},"references-count":22,"alternative-id":["10.1145\/2108616.2108661","10.1145\/2108616"],"URL":"https:\/\/doi.org\/10.1145\/2108616.2108661","relation":{},"subject":[],"published":{"date-parts":[[2010,1,14]]},"assertion":[{"value":"2010-01-14","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}