{"id":197568,"created":"2025-01-19T01:02:00.330581+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00197568","sets":["1164:4179:9731:9822"]},"path":["9822"],"owner":"44499","recid":"197568","title":["Clustering of Text Documents using Features from Latent Semantic Analysis"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-06-06"},"_buckets":{"deposit":"c3382c50-30ad-43fe-868d-9ca989453306"},"_deposit":{"id":"197568","pid":{"type":"depid","value":"197568","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Clustering of Text Documents using Features from Latent Semantic Analysis","author_link":["474205","474207","474200","474203","474204","474201","474206","474202"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Clustering of Text Documents using Features from Latent Semantic Analysis"},{"subitem_title":"Clustering of Text Documents using Features from Latent Semantic Analysis","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"言語処理応用","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-06-06","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University"},{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University"},{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University"},{"subitem_text_value":"Department of Information Management, Chaoyang University of Technology"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University","subitem_text_language":"en"},{"subitem_text_value":"Faculty of Software and Information Science, Iwate Prefectural University","subitem_text_language":"en"},{"subitem_text_value":"Department of Information Management, Chaoyang University of Technology","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"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/197568/files/IPSJ-NL19240005.pdf","label":"IPSJ-NL19240005.pdf"},"date":[{"dateType":"Available","dateValue":"2021-06-06"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-NL19240005.pdf","filesize":[{"value":"887.4 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":"23"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"4b08b7df-f108-44bf-a6a7-4d48fdebc501","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shu-Cih, Tseng"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yu-Ching, Lu"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Goutam, Chakraborty"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Long-Sheng, Chen"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Shu-Cih, Tseng","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Yu-Ching, Lu","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Goutam, Chakraborty","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Long-Sheng, Chen","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN10115061","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":"2188-8779","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Text documents could be classified using words as features. As the number of words in the vocabulary is large, the dimension of the document space will be very high. In that case, the feature vector for a document is too long, and clustering and classification algorithms fail. There are various ways to reduce this dimension by topic modeling. In this work, we used Latent Semantic Analysis (LSA), which is actuated by Singular Value Decomposition (SVD). After SVD, we have a compact representation of the documents, which are clustered. The ground truth is verified manually. In this work, we used tourists' comments as documents. Tourists visit to a place is influenced by comments from previous visitors. In this work, we first cluster the comments into two, and investigate the factors behind these two classes. It is verified, that the documents are automatically separated into groups of positive comments and negative comments. Our final goal is to extract factors that lead to positive comments and those leading to negative comments. That would help promoting tourist business by focusing on the factors that really matters for the customers.","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Text documents could be classified using words as features. As the number of words in the vocabulary is large, the dimension of the document space will be very high. In that case, the feature vector for a document is too long, and clustering and classification algorithms fail. There are various ways to reduce this dimension by topic modeling. In this work, we used Latent Semantic Analysis (LSA), which is actuated by Singular Value Decomposition (SVD). After SVD, we have a compact representation of the documents, which are clustered. The ground truth is verified manually. In this work, we used tourists' comments as documents. Tourists visit to a place is influenced by comments from previous visitors. In this work, we first cluster the comments into two, and investigate the factors behind these two classes. It is verified, that the documents are automatically separated into groups of positive comments and negative comments. Our final goal is to extract factors that lead to positive comments and those leading to negative comments. That would help promoting tourist business by focusing on the factors that really matters for the customers.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","bibliographic_titles":[{"bibliographic_title":"研究報告自然言語処理（NL）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2019-06-06","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"5","bibliographicVolumeNumber":"2019-NL-240"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T22:18:14.867022+00:00","links":{}}