{"id":9861,"updated":"2025-01-23T03:09:41.311634+00:00","links":{},"created":"2025-01-18T22:44:57.812846+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00009861","sets":["581:599:604"]},"path":["604"],"owner":"1","recid":"9861","title":["プログラム理解を支援するコンセプトキーワードの自動抽出法ckTF/IDF法の提案"],"pubdate":{"attribute_name":"公開日","attribute_value":"2007-08-15"},"_buckets":{"deposit":"1d74d731-c01e-4a87-86bd-fceed1fff644"},"_deposit":{"id":"9861","pid":{"type":"depid","value":"9861","revision_id":0},"owners":[1],"status":"published","created_by":1},"item_title":"プログラム理解を支援するコンセプトキーワードの自動抽出法ckTF/IDF法の提案","author_link":["0","0"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"プログラム理解を支援するコンセプトキーワードの自動抽出法ckTF/IDF法の提案"},{"subitem_title":"ckTF/IDF: a Method for Automatically Extracting Concept Keywords for Program Understanding","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"特集：ソフトウェア工学の理論と実践","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2007-08-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"東京工業大学大学院情報理工学研究科計算工学専攻"},{"subitem_text_value":"東京工業大学大学院情報理工学研究科計算工学専攻"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology","subitem_text_language":"en"},{"subitem_text_value":"Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology","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/9861/files/IPSJ-JNL4808010.pdf"},"date":[{"dateType":"Available","dateValue":"2009-08-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL4808010.pdf","filesize":[{"value":"404.0 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"987a20f4-9ac9-486e-ac27-4c33a97704fa","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2007 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"大場, 勝"},{"creatorName":"権藤, 克彦"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Masaru, Ohba","creatorNameLang":"en"},{"creatorName":"Katsuhiko, Gondow","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"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_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":"本論文では，識別子からコンセプトキーワードを発見するためのckTF/IDF（Concept Keyword Term Frequency/Inverse Document Frequency）法を提案する．ckTF/IDF 法は大規模なソフトウェアにおけるコンセプトキーワードの抽出に適している．その理由は以下の2 つである．1 つ目は，ckTF/IDF 法はTF/IDF 法に比べ非常に軽量であること．2 つ目は識別子からコンセプトキーワードを抽出するための発見的手法を導入している点である．我々は，教育用OS udos（約5 000 行）とgcc（GNU Compiler Collection，約90 万行）とを事例に予備実験を行った．予備実験の結果，ckTF/IDF 法によるコンセプトキーワードの計算速度は，gcc の場合，TF/IDF 法と比べ新規検索で約6 倍，ファイル更新にともなう再計算で約890 倍も高速だった．コンセプトキーワードの抽出の精度と再現率は，udos の場合で，それぞれ57%と26%だった．これは，我々のアプローチが識別子におけるコンセプトキーワードの抽出に向いていることを示している．今後の課題は，たとえば，ckTF/IDF 法を使って高速で精度の高いソースコード検索エンジンを開発することといった，コンセプトキーワードの応用である．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"We propose the Concept Keyword Term Frequency/Inverse Document Frequency (ckTF/IDF) method as a novel technique to efficiency mine concept keywords from identifiers in large software projects. ckTF/IDF is suitable for mining concept keywords，since the ckTF/IDF is more lightweight than the TF/IDF method，and the ckTF/IDF’s heuristics is tuned for identifiers in programs. We then experimentally apply the ckTF/IDF to our educational operating system udos (consisting of around 5,000 lines in C code) and GNU C Compiler Collection (gcc, consisting of around 900,000 lines in C code), which produced promising results; By ckTF/IDF method, The gcc’s source code was processed in 6 times faster than TF/IDF method at first time, and in 891 times faster than TF/IDF method at updating the source code. the udos’s source code was processed with an accuracy of around 57%. This preliminary result suggests that our approach is useful for mining concept keywords from identifiers, although we need more research and experience. For example, ckTF/IDF method can apply to fast source code search engine.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"2607","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"2596","bibliographicIssueDates":{"bibliographicIssueDate":"2007-08-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"8","bibliographicVolumeNumber":"48"}]},"relation_version_is_last":true,"item_2_alternative_title_2":{"attribute_name":"その他タイトル","attribute_value_mlt":[{"subitem_alternative_title":"テスト技法・保守技術"}]},"weko_creator_id":"1"}}