{"created":"2025-01-19T01:11:35.569561+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00210365","sets":["581:10433:10436"]},"path":["10436"],"owner":"44499","recid":"210365","title":["多観点類似度を用いた凝集型階層クラスタリング"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-03-15"},"_buckets":{"deposit":"56a71c11-c637-4cb9-805d-b2eccaa9b7bd"},"_deposit":{"id":"210365","pid":{"type":"depid","value":"210365","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"多観点類似度を用いた凝集型階層クラスタリング","author_link":["532428","532431","532430","532429"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"多観点類似度を用いた凝集型階層クラスタリング"},{"subitem_title":"Application of MultiViewpoint-based Similarity to Hierarchical Clustering","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"[一般論文] 階層クラスタリング，多観点，類似度，時間計算量，群平均法","subitem_subject_scheme":"Other"}]},"item_type_id":"2","publish_date":"2021-03-15","item_2_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"電気通信大学"},{"subitem_text_value":"電気通信大学"}]},"item_2_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The University of Electro-Communications","subitem_text_language":"en"},{"subitem_text_value":"The University of Electro-Communications","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/210365/files/IPSJ-JNL6203022.pdf","label":"IPSJ-JNL6203022.pdf"},"date":[{"dateType":"Available","dateValue":"2023-03-15"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-JNL6203022.pdf","filesize":[{"value":"572.1 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":"8"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"98c161e7-ae09-48e9-9ec9-d125e3f76635","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Information Processing Society of Japan"}]},"item_2_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"藤原, 勇二"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"古賀, 久志"}],"nameIdentifiers":[{}]}]},"item_2_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Yuji, Fujiwara","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Hisashi, Koga","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":"cosine類似度は文書クラスタリングで頻繁に使われる代表的な類似度であり，2点間の類似度を原点を基準点（始点）とする2ベクトルのなす角度から決定する．近年，ベクトルの基準点を原点ではなくデータセット内の様々な点に移動して類似度を計算する多観点類似度MVS（MultiViewpoint-based Similarity）が提案され，非階層クラスタリングにおいてcosine類似度よりも高い分類性能を達成した．本研究ではMVSを，階層クラスタリングとくに群平均法と組み合わせたクラスタリングアルゴリズムMVS-AVEを提案する．MVSはcosine類似度よりも複雑であるにもかかわらず，MVS-AVEはクラスタ間類似度を高速計算する工夫により，cosine類似度を利用した群平均法CS-AVEと同等の時間計算量で動作する．実文書データを用いた評価実験により，MVS-AVEが，CS-AVEと比べて計算時間をほとんど増やさずに分類精度を向上できることを示す．さらに，MVS-AVEはクラスタサイズ（各クラスタのメンバ数）の均衡性をコントロールする仕組みを容易に導入できるという面白い特徴を持つ．","subitem_description_type":"Other"}]},"item_2_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"The cosine similarity is a similarity measure useful for document clustering. The cosine similarity between two points is determined by the angle between their corresponding vectors which start from the origin. Recently, a new similarity measure called MVS (MultiViewpoint-based Similarity) which observes the vectors from multiple viewpoints is proposed. MVS is shown to outperform the cosine similarity, when they are combined with some non-hierarchical clustering algorithm. This paper proposes an agglomerative hierarchical clustering named as MVS-AVE which couples the average-link method with MVS. Despite MVS is more complex than the cosine similarity, MVS-AVE achieves the same time complexity as the average-link method with the cosine similarity because of an effort to compute the inter-cluster similarity efficiently. Experimentally in document clustering, MVS-AVE outputs more accurate clustering results than the average-link method with the cosine similarity almost without lengthening the running time. Interestingly, our algorithm can be expanded to control the size fairness among clusters.","subitem_description_type":"Other"}]},"item_2_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"945","bibliographic_titles":[{"bibliographic_title":"情報処理学会論文誌"}],"bibliographicPageStart":"936","bibliographicIssueDates":{"bibliographicIssueDate":"2021-03-15","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"3","bibliographicVolumeNumber":"62"}]},"relation_version_is_last":true,"item_2_identifier_registration":{"attribute_name":"ID登録","attribute_value_mlt":[{"subitem_identifier_reg_text":"10.20729/00210263","subitem_identifier_reg_type":"JaLC"}]},"weko_creator_id":"44499"},"id":210365,"updated":"2025-01-19T18:05:06.134175+00:00","links":{}}