{"created":"2025-01-19T01:27:17.501164+00:00","updated":"2025-01-19T11:58:01.870485+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00228045","sets":["6164:6165:6640:11353"]},"path":["11353"],"owner":"44499","recid":"228045","title":["スマートフォンの利用履歴に着目したBig Five推定モデルの提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-06-28"},"_buckets":{"deposit":"8699847d-f4f4-416d-983f-453e7a05c6bb"},"_deposit":{"id":"228045","pid":{"type":"depid","value":"228045","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"スマートフォンの利用履歴に着目したBig Five推定モデルの提案","author_link":["608609","608611","608610","608608"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"スマートフォンの利用履歴に着目したBig Five推定モデルの提案"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"実空間データ分析，AI","subitem_subject_scheme":"Other"}]},"item_type_id":"18","publish_date":"2023-06-28","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_18_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"株式会社NTTドコモ"},{"subitem_text_value":"株式会社NTTドコモ"},{"subitem_text_value":"株式会社NTTドコモ"},{"subitem_text_value":"株式会社NTTドコモ"}]},"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/228045/files/IPSJ-DICOMO2023015.pdf","label":"IPSJ-DICOMO2023015.pdf"},"date":[{"dateType":"Available","dateValue":"2025-06-28"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-DICOMO2023015.pdf","filesize":[{"value":"1.3 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":"44"}],"accessrole":"open_date","version_id":"adda09c7-573d-4042-b161-bc3274652a35","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_18_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"山下, 毅"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"濱谷, 尚志"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"土井, 千章"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"檜山, 聡"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_18_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"近年，パーソナルデータの活用は進んでいるが，ユーザの性格 (パーソナリティ) を考慮した取り組みに関しては解決すべき課題がある．パーソナリティの 1 つとして広く用いられている Big Five は，質問紙やインタビューを通じて取得するのが一般的であるが，対象とするサービスの全ユーザから取得するには，ユーザやサービス提供者に多大なコストがかかり困難である．そのため本研究では，スマートフォンから取得可能な利用履歴を用いて，Big Five を推定する手法を提案する．本研究の貢献として，7,850 人を対象として，スマートフォンの利用履歴と Big Five に関するデータを収集し，Big Five の分布及び年齢や性差などの分析を行い，Big Five の各因子の得点を推定する機械学習モデルを構築したことが挙げられる．結果として，Big Five の 5 つの因子の観測値と本手法による予測値の相関係数に関して，.22-.41 を確認した．","subitem_description_type":"Other"}]},"item_18_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"107","bibliographic_titles":[{"bibliographic_title":"マルチメディア，分散，協調とモバイルシンポジウム2023論文集"}],"bibliographicPageStart":"100","bibliographicIssueDates":{"bibliographicIssueDate":"2023-06-28","bibliographicIssueDateType":"Issued"},"bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":228045,"links":{}}