學術產出-期刊論文

文章檢視/開啟

書目匯出

Google ScholarTM

政大圖書館

引文資訊

TAIR相關學術產出

題名 基於文本分析的綜合關係網路建模—以海外台灣左翼資料庫為例
Exploring Interpersonal Networks Based on Text Analysis: Insights from the Overseas Taiwanese Leftist Database
作者 吳怡潔;薛化元
Wu, Yi-Chieh;Hsueh, Hua-Yuan
貢獻者 圖資與檔案學刊
關鍵詞 自然語言處理; 深度學習; 命名實體識別; 綜合關係網路; 資料視覺化
Natural Language Processing; Deep Learning; Named Entity Recognition; Interpersonal Relationship Network; Data Visualization
日期 2024-06
上傳時間 12-九月-2024 15:15:53 (UTC+8)
摘要 本論文取材自左派運動領導者左雄主導的「台灣時代社」等數位典藏。該資料庫收錄台灣時代社 1970-2018 年間所出版的雜誌、內部通訊及成員間往來書信,共計文檔 498 件,內文 229 萬字。在全文數位化後,我們利用自然語言處理技術,進行命名實體識別、尋找關鍵詞語、統計重點詞彙頻率,並爬梳成員間的社會網路關係,分析結果以動態的資料視覺化呈現。如此綜合各種面向、關係的網路圖,讓研究者能探討各種關切因素,同時透過視覺化分析結果,更深入地瞭解其中的量化資訊,期盼本文成果可作為輔助社會科學領域質性與量化研究的便利工具。
This study utilizes the digital archives of the “Taiwan Sitai,” led by the leftist movement leader Tso Hsiung. The database comprises 498 documents totaling 2.29 million words, including magazines, internal newsletters, and member correspondence, spanning from 1970 to 2018. Through advanced natural language processing techniques such as named entity recognition (NER) and keyword extraction (key terms), we analyzed the social network dynamics among members. The findings are illustrated with dynamic data visualizations that provide comprehensive network graphs, capturing diverse relationships and facets. Such visualizations serve as convenient tools to assist qualitative and quantitative research in social sciences.
關聯 圖資與檔案學刊, 104, 38-68
資料類型 article
DOI https://doi.org/10.6575/JILA.202406_(104).0002
dc.contributor 圖資與檔案學刊
dc.creator (作者) 吳怡潔;薛化元
dc.creator (作者) Wu, Yi-Chieh;Hsueh, Hua-Yuan
dc.date (日期) 2024-06
dc.date.accessioned 12-九月-2024 15:15:53 (UTC+8)-
dc.date.available 12-九月-2024 15:15:53 (UTC+8)-
dc.date.issued (上傳時間) 12-九月-2024 15:15:53 (UTC+8)-
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/153778-
dc.description.abstract (摘要) 本論文取材自左派運動領導者左雄主導的「台灣時代社」等數位典藏。該資料庫收錄台灣時代社 1970-2018 年間所出版的雜誌、內部通訊及成員間往來書信,共計文檔 498 件,內文 229 萬字。在全文數位化後,我們利用自然語言處理技術,進行命名實體識別、尋找關鍵詞語、統計重點詞彙頻率,並爬梳成員間的社會網路關係,分析結果以動態的資料視覺化呈現。如此綜合各種面向、關係的網路圖,讓研究者能探討各種關切因素,同時透過視覺化分析結果,更深入地瞭解其中的量化資訊,期盼本文成果可作為輔助社會科學領域質性與量化研究的便利工具。
dc.description.abstract (摘要) This study utilizes the digital archives of the “Taiwan Sitai,” led by the leftist movement leader Tso Hsiung. The database comprises 498 documents totaling 2.29 million words, including magazines, internal newsletters, and member correspondence, spanning from 1970 to 2018. Through advanced natural language processing techniques such as named entity recognition (NER) and keyword extraction (key terms), we analyzed the social network dynamics among members. The findings are illustrated with dynamic data visualizations that provide comprehensive network graphs, capturing diverse relationships and facets. Such visualizations serve as convenient tools to assist qualitative and quantitative research in social sciences.
dc.format.extent 2573016 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) 圖資與檔案學刊, 104, 38-68
dc.subject (關鍵詞) 自然語言處理; 深度學習; 命名實體識別; 綜合關係網路; 資料視覺化
dc.subject (關鍵詞) Natural Language Processing; Deep Learning; Named Entity Recognition; Interpersonal Relationship Network; Data Visualization
dc.title (題名) 基於文本分析的綜合關係網路建模—以海外台灣左翼資料庫為例
dc.title (題名) Exploring Interpersonal Networks Based on Text Analysis: Insights from the Overseas Taiwanese Leftist Database
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.6575/JILA.202406_(104).0002
dc.doi.uri (DOI) https://doi.org/10.6575/JILA.202406_(104).0002