{"links":{},"id":2004340,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:02004340","sets":["581:11839:11848"]},"path":["11848"],"owner":"80578","recid":"2004340","title":["社会共同体における対リスク施策決定議論を支援するAIシステム"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2025-09-15"},"_buckets":{"deposit":"43937231-1758-4451-955d-f92b58322fe3"},"_deposit":{"id":"2004340","pid":{"type":"depid","value":"2004340","revision_id":0},"owner":"80578","owners":[80578],"status":"published","created_by":80578},"item_title":"社会共同体における対リスク施策決定議論を支援するAIシステム","author_link":[],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"社会共同体における対リスク施策決定議論を支援するAIシステム","subitem_title_language":"ja"},{"subitem_title":"AI System to Support Discussions to Determine Measures Against Risks in Social Communities","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[特集:AI社会を安全にするコンピュータセキュリティ技術] 人間-AI協調，リスクコミュニケーション，大規模言語モデル，社会的合意形成，施策決定","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2025-09-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社GRI"},{"subitem_text_value":"東京電機大学未来科学部"},{"subitem_text_value":"東京電機大学大学院未来科学研究科"},{"subitem_text_value":"東京電機大学サイバーセキュリティ研究所"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"GRI Incorporated","subitem_text_language":"en"},{"subitem_text_value":"School of Science and Technology for Future Life, Tokyo Denki University","subitem_text_language":"en"},{"subitem_text_value":"Graduate School of Science and Technology for Future Life, Tokyo Denki University","subitem_text_language":"en"},{"subitem_text_value":"Cyber Security Laboratories, Tokyo Denki University","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/2004340/files/IPSJ-JNL6609019.pdf","label":"IPSJ-JNL6609019.pdf"},"date":[{"dateType":"Available","dateValue":"2027-09-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6609019.pdf","filesize":[{"value":"1.7 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"b2e14de3-fbce-4643-81e0-66c0f453cf64","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2025 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大前,俊暁"}]},{"creatorNames":[{"creatorName":"山田,剛一"}]},{"creatorNames":[{"creatorName":"増田,英孝"}]},{"creatorNames":[{"creatorName":"佐々木,良一"}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Toshiaki Ohmae","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Koichi Yamada","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Hidetaka Masuda","creatorNameLang":"en"}]},{"creatorNames":[{"creatorName":"Ryoichi Sasaki","creatorNameLang":"en"}]}]},"item_2_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00116647","subitem_source_identifier_type":"NCID"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_6501","resourcetype":"journal article"}]},"item_2_publisher_15":{"attribute_name":"公開者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"item_2_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"1882-7764","subitem_source_identifier_type":"ISSN"}]},"item_2_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"本研究では，社会共同体におけるリスク対策などの施策決定議論を支援することを目的とし，LLMを活用した議論支援AIシステムの構想を提案し，その中核機能である意見生成部分の有効性を評価する．現代社会では，多様な利害関係者間の合意形成が課題となっており，効率的かつ公平な意思決定プロセスが求められている．そこで本研究では，大規模言語モデル（LLM）を活用し，議論予測，意見抽出，意見補完機能を持つ議論支援AIシステムを開発する．実験では，青少年のインターネット利用制限に関する議論を対象とする．実験目的は，提案システムの中核をなすLLMによる意見生成（議論予測・意見抽出・意見補完）機能の質と，それが議論のサブファシリテータによる有望なコメントの選別プロセスに与える影響を検証することである．9名の実験協力者を用いて実験を行った結果，AIによる支援が議論の質と効率性を向上させ，人間の判断とAIの判断が相補的に機能することが示された．本研究の成果は，AI技術を活用した新たな集団意思決定支援の一部機能の可能性を示すとともに，社会共同体における合意形成プロセスの改善に貢献するための基礎的知見を提供する．今後の課題として，より大規模な実験による検証や，異なる社会的文脈における適用可能性の探究があげられる．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"In this research, we propose a concept for an LLM-based discussion support AI system aimed at supporting decision-making discussions on risk measures and other policies in social communities, and evaluate the effectiveness of the opinion generation component, which is the core function of the system. In modern society, consensus building among diverse stakeholders has become a challenge, requiring efficient and fair decision-making processes. Therefore, in this research, we develop a discussion support AI system using large language models (LLMs) that includes functions for discussion prediction, opinion extraction, and opinion supplementation. In our experiments, we focus on discussions regarding internet usage restrictions for young people. The purpose of the experiment is to verify the quality of the opinion generation (discussion prediction, opinion extraction, opinion completion) function by LLMs, which forms the core of the proposed system, and its impact on comment selection by discussion facilitators. As a result of experiments conducted with 9 subjects, it was shown that AI support improves the quality and efficiency of discussions, and that human judgment and AI judgment function complementarily. The results of this research demonstrate the potential of some functions of AI technology for new group decision-making support and provide fundamental insights for contributing to the improvement of consensus-building processes in social communities. Future challenges include verification through larger-scale experiments and exploration of applicability in different social contexts.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"1234","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"1218","bibliographicIssueDates":{"bibliographicIssueDate":"2025-09-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"66"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/0002004340","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"80578"},"created":"2025-09-05T04:46:51.385627+00:00","updated":"2025-09-15T23:06:51.682687+00:00"}