{"id":227734,"updated":"2025-01-19T12:05:20.659308+00:00","links":{},"created":"2025-01-19T01:26:59.279181+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00227734","sets":["1164:1165:11326:11327"]},"path":["11327"],"owner":"44499","recid":"227734","title":["対照学習を用いたニュースの潜在的な関係性の抽出と可視化"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-09-14"},"_buckets":{"deposit":"62fc9ef6-2f39-470c-b1e4-d16982dd1fbb"},"_deposit":{"id":"227734","pid":{"type":"depid","value":"227734","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"対照学習を用いたニュースの潜在的な関係性の抽出と可視化","author_link":["607067","607068","607066","607065"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"対照学習を用いたニュースの潜在的な関係性の抽出と可視化"},{"subitem_title":"Extracting and visualizing latent relationships in news using contrastive learning","subitem_title_language":"en"}]},"item_type_id":"4","publish_date":"2023-09-14","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"九州大学大学院芸術工学府"},{"subitem_text_value":"九州大学大学院芸術工学研究院"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Graduate School of Design, Kyushu University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Design, Kyushu 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/227734/files/IPSJ-DBS23177002.pdf","label":"IPSJ-DBS23177002.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DBS23177002.pdf","filesize":[{"value":"1.9 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"13"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"3b80ad48-6ede-4bb3-bdb2-38abf90400fd","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"高橋, 陸"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"牛尼, 剛聡"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Riku, Takahashi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Taketoshi, Ushiama","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_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-871X","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年 SNS の普及に伴い,ユーザが興味のあるトピックに関する情報収集を行う際に SNS を用いることが一般化した.SNS を用いた情報収集では,リアルタイムで更新される情報や投稿者から直接意見が得られるなどの利点がある.一般的に SNS を用いて情報収集する際,対象とするトピックに関連する単語をキーワードとして検索を行うキーワード検索を用いる.しかし,SNS はユーザが個別に投稿を行うため,情報が整理されていないことから,同一のトピックに関する投稿であっても含まれるキーワードが一致していない場合が多い,そのため,SNS からユーザが興味を持つトピックに関する意見や反応を網羅的に検索するのは困難である.本研究では,Twitter 上に投稿されたニュース記事と,それに対するリプライに着目し,機械学習を用いてニュースとリプライの関係を学習することで,ニュースに対する社会的反応の特徴を抽出する手法を提案する.本手法では,ニュース記事とリプライの文章ベクトルから,同一ニュースに関する投稿の文章ベクトル間の類似度が高くなるように学習を行うことで,投稿から類似度の高いニュースを求め,ユーザが興味を持ったニュースに関連する情報を提示することで情報収集を支援する.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告データベースシステム(DBS)"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2023-09-14","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"2","bibliographicVolumeNumber":"2023-DBS-177"}]},"relation_version_is_last":true,"weko_creator_id":"44499"}}