{"created":"2025-01-18T23:29:09.612258+00:00","updated":"2025-01-21T23:46:45.822120+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00069785","sets":["1164:2735:6033:6124"]},"path":["6124"],"owner":"11","recid":"69785","title":["Webアーカイブにおける差分収集に用いるWebページの更新依存度分析"],"pubdate":{"attribute_name":"公開日","attribute_value":"2010-07-05"},"_buckets":{"deposit":"7dc023a7-49bb-499c-93b7-8a46cfb44898"},"_deposit":{"id":"69785","pid":{"type":"depid","value":"69785","revision_id":0},"owners":[11],"status":"published","created_by":11},"item_title":"Webアーカイブにおける差分収集に用いるWebページの更新依存度分析","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Webアーカイブにおける差分収集に用いるWebページの更新依存度分析"},{"subitem_title":"Update Dependence Analysis of Web Pages for Incremental Crawling","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2010-07-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"奈良女子大学大学院人間文化研究科"},{"subitem_text_value":"奈良女子大学大学院人間文化研究科"},{"subitem_text_value":"奈良女子大学大学院人間文化研究科"},{"subitem_text_value":"奈良女子大学大学院人間文化研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Humanities and Sciences, Nara Women's University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Humanities and Sciences, Nara Women's University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Humanities and Sciences, Nara Women's University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Humanities and Sciences, Nara Women's University","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/69785/files/IPSJ-MPS10079008.pdf"},"date":[{"dateType":"Available","dateValue":"2012-07-05"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-MPS10079008.pdf","filesize":[{"value":"597.1 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":"17"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"7c7ba535-c2ea-45ec-afbc-b12a6a4389d2","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2010 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"廣道, 尚弓"},{"creatorName":"吉井, 直子"},{"creatorName":"高田, 雅美"},{"creatorName":"城, 和貴"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Naomi, Hiromichi","creatorNameLang":"en"},{"creatorName":"Naoko, Yoshii","creatorNameLang":"en"},{"creatorName":"Masami, Takata","creatorNameLang":"en"},{"creatorName":"Kazuki, Joe","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10505667","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":"膨大な数の Web サイトが開設され、それらの多くが定期的、または不定期に更新されるため、Web アーカイブが重要となっている。そこで、Web クローラはいつ収集すべきかという問題に直面している。特に、差分収集は Web ページを収集するにあたり、収集間隔が重要な問題となる。本稿では、Interval Graph と Heap Tree 構造を用いて、差分収集に用いる適切な収集間隔を予測するための新たなモデルを提案する。そのモデルは Web ページの更新依存度を用いて Web サイトの更新間隔を推定する。モデルの予備実験は本稿で示す。","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"As huge number of web sites are created anywhere, Web archiving is an important task since most Web sites are updated periodically or non periodically. Any web crawler faces to the problem of ”When should we collect?”. Especially, incremental crawling has an essential problem of time interval for web page collections. In this paper, we propose a new model to predict the appropriate interval time for incremental web crawling by using an extended interval graph and heap tree structures. The model estimates the update interval of web pages in a web site with the information of modification dependence information of the web pages. Preliminary experiment of the model is shown in the paper.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告数理モデル化と問題解決（MPS）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2010-07-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"2010-MPS-79"}]},"relation_version_is_last":true,"weko_creator_id":"11"},"id":69785,"links":{}}