{"updated":"2025-01-22T00:55:08.240992+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00066699","sets":["1164:1165:5677:5916"]},"path":["5916"],"owner":"10","recid":"66699","title":["スプログ検出におけるHTML構造の類似性の有効性の評価"],"pubdate":{"attribute_name":"公開日","attribute_value":"2009-11-13"},"_buckets":{"deposit":"30688ca0-733e-4d9c-b642-f6daa5bd11cd"},"_deposit":{"id":"66699","pid":{"type":"depid","value":"66699","revision_id":0},"owners":[10],"status":"published","created_by":10},"item_title":"スプログ検出におけるHTML構造の類似性の有効性の評価","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"スプログ検出におけるHTML構造の類似性の有効性の評価"},{"subitem_title":"Evaluating Effects of Similarities of HTML Structures in Splog Detection","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション：ブログ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2009-11-13","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"筑波大学大学院システム情報工学研究科"},{"subitem_text_value":"東京電機大学大学院工学研究科"},{"subitem_text_value":"筑波大学大学院システム情報工学研究科"},{"subitem_text_value":" (株) ナビックス"},{"subitem_text_value":"東京大学人工物工学研究センター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Systems and Information Engineering, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Engineering, Tokyo Denki University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Systems and Information Engineering, University of Tsukuba","subitem_text_language":"en"},{"subitem_text_value":"Navix Co., Ltd.","subitem_text_language":"en"},{"subitem_text_value":"Research into Artifacts, Center for Engineering, University of Tokyo","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/66699/files/IPSJ-DBS09149019.pdf"},"date":[{"dateType":"Available","dateValue":"2011-11-13"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS09149019.pdf","filesize":[{"value":"868.2 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"7c396a6f-bb3c-4730-8802-b3aacc97fbde","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2009 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"片山, 太一"},{"creatorName":"芳中, 隆幸"},{"creatorName":"宇津呂, 武仁"},{"creatorName":"河田, 容英"},{"creatorName":"福原, 知宏"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Taichi, Katayama","creatorNameLang":"en"},{"creatorName":"Takayuki, Yoshinaka","creatorNameLang":"en"},{"creatorName":"Takehito, Utsuro","creatorNameLang":"en"},{"creatorName":"Yasuhide, Kawada","creatorNameLang":"en"},{"creatorName":"Tomohiro, Fukuhara","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10112482","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，ブログにおいてアフィリエイト収入を得ることを目的とするスパム (スパムブログ，スプログ) のうち，特に，同一のスパムブログ作成者が自動的に大量生成したと推測されるスプログの検出において，HTML 構造の類似性が効果的であることを示す．具体的には，ブログの HTML ファイルにおける DOM ツリーから，コンテンツの最小単位に相当するブロックを抽出し，複数のスプログの間でブロック構造の類似性を測定する．その結果，同一ブログホストにおけるスプログのうち，同一のスパムブログ作成者が自動的に大量生成したと推測されるスプログ同士では，ブロック構造が類似する傾向があることを示す．また，ブロック構造の類似性を素性として用いることにより，SVM によるスプログ検出の性能が向上する場合があることを示す．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Spam blogs or splogs are blogs hosting spam posts, created using machine generated or hijacked content for the sole purpose of hosting advertisements or raising the number of inward of target sites. Among those splogs, this paper focuses on detecting a group of splogs which are estimated to be created by an identical spammer. We especially show that similarities of html structures among those splogs created by an identical spammer contribute to improving the performance of splog detection. In measuring similarities of html structures, we extract a list of blocks (minimum unit of content) from the DOM tree of a html file. We show that the html files of splogs estimated to be created by an identical spammer tend to have similar DOM trees and this tendency is quite effective in splog detection.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"8","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム（DBS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2009-11-13","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"19","bibliographicVolumeNumber":"2009-DBS-149"}]},"relation_version_is_last":true,"weko_creator_id":"10"},"created":"2025-01-18T23:27:24.137833+00:00","id":66699,"links":{}}