WEKO3
アイテム
{"_buckets": {"deposit": "fea67148-5c78-4c70-b50c-ff68018bc486"}, "_deposit": {"created_by": 17, "id": "2009955", "owner": "17", "owners": [17], "pid": {"revision_id": 0, "type": "depid", "value": "2009955"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:02009955", "sets": ["1712290737257"]}, "author_link": [], "item_1615768549627": {"attribute_name": "出版タイプ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_9_alternative_title_19": {"attribute_name": "その他のタイトル", "attribute_value_mlt": [{"subitem_alternative_title": "A Comparative Study of Text Mining Techniques for Content Extraction : Using Analysis of Policy Speeches by Japanese Prime Ministers as an Example", "subitem_alternative_title_language": "en"}]}, "item_9_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2024-03-31", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "100", "bibliographicPageStart": "85", "bibliographicVolumeNumber": "7", "bibliographic_titles": [{"bibliographic_title": "名古屋大学人文学研究論集", "bibliographic_titleLang": "ja"}, {"bibliographic_title": "The Journal of Humanities, Nagoya University", "bibliographic_titleLang": "en"}]}]}, "item_9_description_4": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "This paper applies TF-IDF values, correspondence analysis, and topic modeling to analyze the speeches of Japanese prime ministers since 2000, grouping them and summarizing their contents while also examining the characteristics of each analysis method. As a result, it was found that there is continuity in Japanese government policy, and regardless of the prime minister’s party affiliation, they continue to address issues inherited from previous cabinets, adapting to domestic and international situations and formulating new policies. These policies consistently prioritize the people, economy, and society. Over time, the focus has shifted through issues such as “education,” “structural reform,” “regional (revitalization),” “(robust) fiscal policy,” “reconstruction (from the great earthquake),” “the world and the future,” and “(responding to) new coronavirus and digitalization.” A review of the distinct characteristics of each analytical method revealed that all of them have their own unique strengths and limitations. Hence, when attempting to extract content from a text, it is advisable to employ these analytical methods in a comprehensive manner. For smaller data sets, the use of correspondence analysis is recommended, whereas for larger sets, topic modeling should be utilized to categorize texts and compile common points of view. Moreover, calculating TF-IDF values enables the identification of distinctive words for each text, thereby facilitating the summarization of document themes and content.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_9_identifier_registration": {"attribute_name": "ID登録", "attribute_value_mlt": [{"subitem_identifier_reg_text": "10.18999/jouhunu.7.85", "subitem_identifier_reg_type": "JaLC"}]}, "item_9_publisher_32": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "名古屋大学人文学研究科", "subitem_publisher_language": "ja"}]}, "item_9_source_id_7": {"attribute_name": "収録物識別子", "attribute_value_mlt": [{"subitem_source_identifier": "2433-233X", "subitem_source_identifier_type": "PISSN"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "毛, 文偉", "creatorNameLang": "ja"}, {"creatorName": "MAO, Wenwei", "creatorNameLang": "en"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_access", "date": [{"dateType": "Available", "dateValue": "2024-04-08"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "jouhunu_7_85.pdf", "filesize": [{"value": "663 KB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "mimetype": "application/pdf", "size": 663000.0, "url": {"objectType": "fulltext", "url": "https://nagoya.repo.nii.ac.jp/record/2009955/files/jouhunu_7_85.pdf"}, "version_id": "a36f76d5-bf9a-45cc-8541-c6b536a01537"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "テキストマイニング", "subitem_subject_scheme": "Other"}, {"subitem_subject": "TF-IDF", "subitem_subject_scheme": "Other"}, {"subitem_subject": "対応分析", "subitem_subject_scheme": "Other"}, {"subitem_subject": "トピックモデル", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Text Mining", "subitem_subject_scheme": "Other"}, {"subitem_subject": "TF-IDF", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Correspondence Analysis", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Topic Modeling", "subitem_subject_scheme": "Other"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "jpn"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "departmental bulletin paper", "resourceuri": "http://purl.org/coar/resource_type/c_6501"}]}, "item_title": "内容抽出のためのテキストマイニング手法の比較研究 : 日本の歴代首相の所信表明演説の内容分析を例に", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "内容抽出のためのテキストマイニング手法の比較研究 : 日本の歴代首相の所信表明演説の内容分析を例に", "subitem_title_language": "ja"}]}, "item_type_id": "40001", "owner": "17", "path": ["1712290737257"], "permalink_uri": "https://doi.org/10.18999/jouhunu.7.85", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2024-04-08"}, "publish_date": "2024-04-08", "publish_status": "0", "recid": "2009955", "relation": {}, "relation_version_is_last": true, "title": ["内容抽出のためのテキストマイニング手法の比較研究 : 日本の歴代首相の所信表明演説の内容分析を例に"], "weko_shared_id": -1}
内容抽出のためのテキストマイニング手法の比較研究 : 日本の歴代首相の所信表明演説の内容分析を例に
https://doi.org/10.18999/jouhunu.7.85
https://doi.org/10.18999/jouhunu.7.8516c07fca-35c3-4be8-99b0-7fbd8739d9fe
名前 / ファイル | ライセンス | アクション |
---|---|---|
jouhunu_7_85.pdf (663 KB)
|
|
Item type | itemtype_ver1(1) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
公開日 | 2024-04-08 | |||||||||
タイトル | ||||||||||
タイトル | 内容抽出のためのテキストマイニング手法の比較研究 : 日本の歴代首相の所信表明演説の内容分析を例に | |||||||||
言語 | ja | |||||||||
その他のタイトル | ||||||||||
その他のタイトル | A Comparative Study of Text Mining Techniques for Content Extraction : Using Analysis of Policy Speeches by Japanese Prime Ministers as an Example | |||||||||
言語 | en | |||||||||
著者 |
毛, 文偉
× 毛, 文偉
|
|||||||||
アクセス権 | ||||||||||
アクセス権 | open access | |||||||||
アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | テキストマイニング | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | TF-IDF | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | 対応分析 | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | トピックモデル | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | Text Mining | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | TF-IDF | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | Correspondence Analysis | |||||||||
キーワード | ||||||||||
主題Scheme | Other | |||||||||
主題 | Topic Modeling | |||||||||
内容記述 | ||||||||||
内容記述 | This paper applies TF-IDF values, correspondence analysis, and topic modeling to analyze the speeches of Japanese prime ministers since 2000, grouping them and summarizing their contents while also examining the characteristics of each analysis method. As a result, it was found that there is continuity in Japanese government policy, and regardless of the prime minister’s party affiliation, they continue to address issues inherited from previous cabinets, adapting to domestic and international situations and formulating new policies. These policies consistently prioritize the people, economy, and society. Over time, the focus has shifted through issues such as “education,” “structural reform,” “regional (revitalization),” “(robust) fiscal policy,” “reconstruction (from the great earthquake),” “the world and the future,” and “(responding to) new coronavirus and digitalization.” A review of the distinct characteristics of each analytical method revealed that all of them have their own unique strengths and limitations. Hence, when attempting to extract content from a text, it is advisable to employ these analytical methods in a comprehensive manner. For smaller data sets, the use of correspondence analysis is recommended, whereas for larger sets, topic modeling should be utilized to categorize texts and compile common points of view. Moreover, calculating TF-IDF values enables the identification of distinctive words for each text, thereby facilitating the summarization of document themes and content. | |||||||||
言語 | en | |||||||||
内容記述タイプ | Abstract | |||||||||
出版者 | ||||||||||
言語 | ja | |||||||||
出版者 | 名古屋大学人文学研究科 | |||||||||
言語 | ||||||||||
言語 | jpn | |||||||||
資源タイプ | ||||||||||
資源タイプresource | http://purl.org/coar/resource_type/c_6501 | |||||||||
タイプ | departmental bulletin paper | |||||||||
出版タイプ | ||||||||||
出版タイプ | VoR | |||||||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||||||
ID登録 | ||||||||||
ID登録 | 10.18999/jouhunu.7.85 | |||||||||
ID登録タイプ | JaLC | |||||||||
収録物識別子 | ||||||||||
収録物識別子タイプ | PISSN | |||||||||
収録物識別子 | 2433-233X | |||||||||
書誌情報 |
ja : 名古屋大学人文学研究論集 en : The Journal of Humanities, Nagoya University 巻 7, p. 85-100, 発行日 2024-03-31 |