Publications-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 檔案文本探勘研究:以特種檔案為例
The Study on Archival Text Mining: A Case Study of Te-Zhong Record Series
作者 邵僅;林巧敏
Shao, Chin;Lin, Chiao-min
貢獻者 圖檔所
關鍵詞 檔案文本分析; 數位人文; 詞彙共現分析; 特種檔案; 文本探勘
Archives text analysis; Digital humanities; Co-occurrence analysis; Te-zhong records; Text mining
日期 2025-12
上傳時間 12-Mar-2026 15:07:19 (UTC+8)
摘要 本研究以中國國民黨「特種檔案」為對象,進行數位人文研究,採用詞頻統計、實體辨識、社會網絡分析與地理資訊系統等功能,探討檔案中人物、組織、事件之核心詞彙分布及共現關係,解析檔案隱藏的內容重點與人物關係網絡,亦對應地理資訊系統呈現各時期重要地點的分布。本研究透過量化數據與視覺化技術,展現特種檔案中無法以人工直觀的重要資訊,並結合質性說明,為檔案內容的分析與詮釋提供新的方法與應用模式,期許能為檔案學與數位史學提供不同的研究取向。
This study focuses on the Kuomintang's "Te-Zhong Archives," employing digital humanities methods such as word frequency analysis, named entity recognition, social network analysis, and geographic information systems. The research explores the distribution of core vocabulary related to individuals, organizations, and events, uncovering key themes and relational networks within the archives. Geographic information systems are utilized to visualize the spatial distribution of significant locations across different periods. Through quantitative data analysis and visualization techniques, this study reveals critical insights embedded in the archives that are difficult to discern through traditional manual examination. By integrating qualitative explanations, it provides new approaches and applications for the analysis and interpretation of archival content, aiming to offer alternative research approaches for archival studies and digital historiography.
關聯 圖書資訊學研究, Vol.20, No.1, pp.47-85
資料類型 article
DOI https://doi.org/10.30177/JLISR.202512_20(1).0002
dc.contributor 圖檔所
dc.creator (作者) 邵僅;林巧敏
dc.creator (作者) Shao, Chin;Lin, Chiao-min
dc.date (日期) 2025-12
dc.date.accessioned 12-Mar-2026 15:07:19 (UTC+8)-
dc.date.available 12-Mar-2026 15:07:19 (UTC+8)-
dc.date.issued (上傳時間) 12-Mar-2026 15:07:19 (UTC+8)-
dc.identifier.uri (URI) https://ah.lib.nccu.edu.tw/item?item_id=181613-
dc.description.abstract (摘要) 本研究以中國國民黨「特種檔案」為對象,進行數位人文研究,採用詞頻統計、實體辨識、社會網絡分析與地理資訊系統等功能,探討檔案中人物、組織、事件之核心詞彙分布及共現關係,解析檔案隱藏的內容重點與人物關係網絡,亦對應地理資訊系統呈現各時期重要地點的分布。本研究透過量化數據與視覺化技術,展現特種檔案中無法以人工直觀的重要資訊,並結合質性說明,為檔案內容的分析與詮釋提供新的方法與應用模式,期許能為檔案學與數位史學提供不同的研究取向。
dc.description.abstract (摘要) This study focuses on the Kuomintang's "Te-Zhong Archives," employing digital humanities methods such as word frequency analysis, named entity recognition, social network analysis, and geographic information systems. The research explores the distribution of core vocabulary related to individuals, organizations, and events, uncovering key themes and relational networks within the archives. Geographic information systems are utilized to visualize the spatial distribution of significant locations across different periods. Through quantitative data analysis and visualization techniques, this study reveals critical insights embedded in the archives that are difficult to discern through traditional manual examination. By integrating qualitative explanations, it provides new approaches and applications for the analysis and interpretation of archival content, aiming to offer alternative research approaches for archival studies and digital historiography.
dc.format.extent 136 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) 圖書資訊學研究, Vol.20, No.1, pp.47-85
dc.subject (關鍵詞) 檔案文本分析; 數位人文; 詞彙共現分析; 特種檔案; 文本探勘
dc.subject (關鍵詞) Archives text analysis; Digital humanities; Co-occurrence analysis; Te-zhong records; Text mining
dc.title (題名) 檔案文本探勘研究:以特種檔案為例
dc.title (題名) The Study on Archival Text Mining: A Case Study of Te-Zhong Record Series
dc.type (資料類型) article
dc.identifier.doi (DOI) 10.30177/JLISR.202512_20(1).0002
dc.doi.uri (DOI) https://doi.org/10.30177/JLISR.202512_20(1).0002