Publications-Theses
Article View/Open
Publication Export
-
題名 數位人文研究平台之階層式主題分析工具發展與應用
Development and Application of Digital Humanities Research Platform with Hierarchical Topic Analysis Tool作者 何偲佑
Ho, Szu-Yu貢獻者 陳志銘
Chen, Chih-Ming
何偲佑
Ho, Szu-Yu關鍵詞 數位人文
主題分析
階層主題建模
文本探勘
資訊視覺化
滯後序列分析
Digital humanities
Topic analysis
Hierarchical topic modeling
Text mining
Information visualization
Lag sequential analysis日期 2020 上傳時間 3-Aug-2020 17:50:50 (UTC+8) 摘要 本研究旨在開發支援數位人文研究之「階層式主題分析工具」，能輔助人文學者，將具時間戳記的相關文本劃分為多個時期，依據各時期之文本進行階層式主題建模，建立一棵屬於該時期、具有樹狀結構之階層式主題模型樹，再透過視覺化的方式呈現，從而輔助人文學者進行文本遠讀分析。同時，亦提供「比較網絡圖」功能，可針對使用者所劃分的時期區段，提供兩個時期之階層主題網絡圖比較，以輔助使用者進行擬探索主題之差異比較，並追蹤特定觀點下的主題概念如何隨著時間而進行變化，進而對文本主題的整體脈絡有更全面的認識。此外，也提供使用者查看來源文本資料的功能，以達到整合細讀和遠讀的輔助主題探索功能。為了驗證此一工具對於支援數位人文研究的效益，本研究以實驗研究法之對抗平衡設計比較實驗對象依序使用有無「階層式主題分析工具」之「羅家倫先生文存數位人文平台」進行文本探索，在所填寫之主題探索評估表得分與探索出相關主題數量與時間上，是否具有顯著的差異；並以科技接受度問卷、半結構訪談的方式瞭解實驗對象對「階層式主題分析工具」的看法與感受；最後，透過滯後序列分析搭配螢幕錄影分析，探討實驗對象操作兩個不同工具的使用行為轉移。實驗結果發現，實驗對象採用具階層式主題分析工具之「羅家倫先生文存數位人文平台」，更能輔助其在短時間內掌握特定觀點下感興趣的文本主題脈絡，並啟發進一步探索之方向。此外，從滯後序列分析結果發現，具階層式主題分析工具之「羅家倫先生文存數位人文平台」所提供之主題詞彙較能符合使用者之期待與需求，並引導使用者連結至相關聯之文本進行閱讀，使其有效與細讀功能進行鏈結。在科技接受度分析與訪談資料分析部分可得知，實驗對象對於具「階層式主題分析工具」之「羅家倫先生文存數位人文平台」持高度正面肯定態度，認為此一工具能輔助其於短時間內掌握特定觀點之主題脈絡與主題內容。但是，認為工具提供之關聯性文本的數量以及萃取出之主題詞彙的精確性仍有進一步改善之空間。在未來研究方向上，可將本工具應用至解讀羅家倫文存以外之其他數位人文領域，探討其帶來之輔助主題脈絡探索效益、亦或嘗試不同主題模型之演算法，以探討不同主題模型支援主題分析的適用性。
This research aims to develop a "Hierarchical Topic Analysis Tool", for supporting research on digital humanities, allowing humanists dividing related texts with time stamp into several periods, and perform hierarchical topic modeling based on the text of each period. The tool will build a hierarchical topic model tree with tree structure belonging to the period, and then present it visually to assist the humanists in the analysis of text distance reading. Meanwhile, "Comparison Network Map" function is provided for assisting users to compare the hierarchical topic network map of the two periods according to the two periods divided by the user. Users are able to compare the differences between the topics they want to explore, and to track how the concept of the topic under a specific viewpoint changes over time, so as to understand the overall context of text topic more comprehensive. In addition, "view source text" function is provided for assisting users to explore topic by combining close reading and distance reading. To verify the effectiveness of "Hierarchical Topic Analysis Tool" in supporting digital humanities research, counterbalanced design in quasi-experimental research is applied in this study to compare the research subjects with and without "Hierarchical Topic Analysis Tool" in Mr. Lo Chia-lun`s Works Digital Humanities Research Platform for text exploration, and if there were significant differences in the score of Topic Explore Form, quantity of exploring related topic and exploring time. Technology acceptance questionnaire and semi-structured interview are utilized for understanding the research subjects’ opinions and perception of “Hierarchical Topic Analysis Tool”. Finally, lag sequential analysis and screen recording analysis are used for observing the research subjects’ behavior processes using two different systems to discuss the notable difference in the operation behavior transfer.The experimental results show that the research subjects who used the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform with "Hierarchical Topic Analysis Tool" could grasp better in the context of the text topic of interest from a specific viewpoint at short notice, and inspire the direction of further exploration than the research subjects who used the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform without "Hierarchical Topic Analysis Tool." Moreover, lag sequential analysis reveals that the topic vocabulary provided by the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform with "Hierarchical Topic Analysis Tool" can accord with the demands of user better. The user is guided to link to the related texts for reading, so that it is able to combine with "close reading" function more effectively. The technology acceptance and interview data analysis reveal highly positive perception of the research subjects on “Hierarchical Topic Analysis Tool”. It presents that such a tool could rapidly assist them grasp the context of topic from a specific viewpoint and content of topic. However, the quantity of related text provided by "Hierarchical Topic Analysis Tool" and accuracy of topic vocabulary still require further improvement. In the future directions, the tool could be used to analyze the other fields of text to discuss the benefit of supporting the users to explore the context of topic, and attempt to apply different algorithms of topic model to compare the applicability of topic model with the one used in the present study.參考文獻 中文文獻中國哲學書電子化計劃(2019)。中國哲學書電子化計劃。上網日期：108年12月20日，檢自：https://ctext.org/zh史雲波(2009)。羅家倫的"五四"觀及其歷史演變。天津社會科學，4(4)，134-137。杜協昌(2018)。DocuSky 與文本字詞關聯圖的視覺化應用。「第九屆數位典藏與數位人文國際研討會」發表之論文，法鼓文理學院。邱偉雲(2019)。主題模型與歷史記憶:數字人文視野下數字記憶史研究理論方法芻議。「文本探勘˙圖像標記-數位工具與人文詮釋國際工作坊」發表之論文，華人文化主體性研究中心。洪瑞嶸(2011)。階層式主題與句子之貝氏非參數模型。國立成功大學資訊工程學系碩博士班碩士論文。粘慈卿(2018)。羅家倫校長學之研究。國立中興大學教師專業發展研究所碩士論文。許小青(2005)。羅家倫與抗戰前的中央大學(1932-1937)。近代中國，163，158-184。郭海俠(2014)。“五四”命名者羅家倫的教育理念與行動。蘭台世界，28，12-13。陳光華、薛弼心(2015)。數位人文研究的在地特性與全球特性之探討。人文與社會科學簡訊，17:1，83-88。陳志銘、林正和(2019)。數位人文研究平台之觀點變遷和年代劃分工具發展與應用。「第十屆數位典藏與數位人文國際研討會」發表之論文。陳奕安(2016)。適用於中文史料文本之標記式主題模型分析方法研究。國立政治大學資訊科學系碩士論文。陳春生(1985)。新文化的旗手:羅家倫傳。近代中國出版社。項潔、涂豐恩(2011)。導論――什麼是數位人文。載於項潔(主編)，從保存到創造: 開啟數位人文研究(9-28頁)。臺北市：國立臺灣大學出版中心。馮夏根(2006)。羅家倫與中國近代史研究。信陽師範學院學報（哲學社會科學版），26(3)，122-124。趙尚杰(2010)。羅家倫高等教育思想研究。中國近現代教育史，8，12-13。趙寧(2016)。簡述羅家倫對近代史料的搜集保存。才智，8，194-195。蕭勝文(2000)。羅家倫與中央大學發展之研究（1932-1941）。國立臺灣師範大學歷史研究所碩士論文。謝曉欣(2015)。教育家羅家倫及其高等教育思想研究。當代教育實踐與教學研究，8，43-44。英文文獻Alencar, A. B., de Oliveira, M. C. F., & Paulovich, F. V. (2012). Seeing beyond reading: a survey on visual text analytics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(6), 476–492. doi:10.1002/widm.1071Analytics Tools & Solutions for Your Business - Google Analytics (n.d.). Retrieved December 20, 2019, from https://marketingplatform.google.com/about/analytics/Bakeman, R., & Gottman, J. M. (1997). Observing interaction: An introduction to sequential analysis, 2nd ed. New York: Cambridge University Press. doi:10.1017/CBO9780511527685Berry, D. (2012). Understanding digital humanities. Springer.Blei D., Ng A., & Jordan M. (2003). Latent dirichlet allocation. The Journal of Machine Learning Research, 3,993-1022.Blei, D. M., Griffiths, T. L., & Jordan, M. I. (2010). The nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies. Journal of the ACM, 57(2), 1-30. doi:10.1145/1667053.1667056Boyles, N. (2013). Closing in on close reading. Educational Leadership,70(4), 36–41.Chen, C. M. & Chang, C. (2019). A Chinese ancient book digital humanities research platform to support digital humanities research. The Electronic Library, 37(2), 314-336.Chen, C. M., Chen, Y. T., & Liu, C. Y. (2019). Development and evaluation of an automatic text annotation system for supporting digital humanities research. Library Hi Tech, 37(3), 436-455.Chen, P., Zhang, N. L., Liu, T., Poon, L. K. M., Chen, Z., & Khawar, F. (2017). Latent tree models for hierarchical topic detection. Artificial Intelligence, 250, 105-124. doi:10.1016/j.artint.2017.06.004Drucker, J. (2013), “Intro to digital humanities: Introduction”, UCLA Center for Digital Humanities. Web available at http://dh101.humanities.ucla.edu/?page_id=13, Retrieved January 28, 2018.Haldar, R., Mukhopadhyay D. (2011). Levenshtein distance technique in dictionary lookup methods: An improved approach. Retrieved from http://arxiv.org/abs/1101.1232Hockey, S. (2004). The history of humanities computing. In R. Siemens & S. Schreibman(Eds.), A Companion to Digital Humanities. Retrieved from http://www.digitalhumanities.org/companion/Hofmann, T. (1999). Probabilistic latent semantic indexing. Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR ’99, 50-57. doi:10.1145/312624.312649Hwang, G.-J., Yang, L.-H., & Wang, S.-Y. (2013). A concept map-embedded educational computer game for improving students’ learning performance in natural science courses. Computers & Education, 69, 121-130.Jänicke, S., Franzini, G., Cheema, M. F., & Scheuermann, G. (2017). Visual text analysis in digital humanities: Visual text analysis in digital humanities. Computer Graphics Forum, 36(6), 226-250. doi:10.1111/cgf.12873Li, Z., Tang, J., Wang, X., Liu, J., & Lu, H. (2016). Multimedia news summarization in search. ACM Transactions on Intelligent Systems and Technology, 7(3), 1–20. doi:10.1145/2822907Liu, T., Zhang, N. L., & Chen, P. (2014). Hierarchical latent tree analysis for topic detection. In T. Calders, F. Esposito, E. Hüllermeier, & R. Meo (Eds.), Machine Learning and Knowledge Discovery in Databases (Vol. 8725, pp. 256-272). Berlin, Heidelberg: Springer Berlin Heidelberg. doi:10.1007/978-3-662-44851-9_17MORETTI, F. (2005). Graphs, Maps, Trees: Abstract Models for a Literary History. Verso, London and New York.Moretti, G., Sprugnoli, R., Menini, S., & Tonelli, S. (2016). ALCIDE: Extracting and visualising content from large document collections to support humanities studies. Knowledge-Based Systems, 111, 100-112.Papadimitriou, C. H., Tamaki, H., Raghavan, P., & Vempala, S. (1998). Latent semantic indexing. Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems - PODS ’98, 159-168. doi:10.1145/275487.275505Rosenzweig, R. (2003). Scarcity or abundance? Preserving the past in a digital era. The American Historical Review, 108(3), 735–762.Stommel, M. & Wills, C.E.(2004). Clinical research: concepts and principles for advanced practice nurses. Philadelphia, Pa.; London: Lippincott Williams & Wilkins.Wei, F., Liu, S., Song, Y., Pan, S., Zhou, M. X., Qian, W., … Zhang, Q. (2010). TIARA: A visual exploratory text analytic system. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’10,153-162. doi:10.1145/1835804.1835827Cui, W., Liu, S., Tan, L., Shi, C., Song, Y., Gao, Z., …Qu, H. (2011). TextFlow: Towards Better Understanding of Evolving Topics in Text. IEEE Transactions on Visualization and Computer Graphics, 17(12), 2412-2421. doi:10.1109/TVCG.2011.239Yang, Y., Yao, Q., & Qu, H. (2017). VISTopic: A visual analytics system for making sense of large document collections using hierarchical topic modeling. Visual Informatics , 1(1), 40-47. doi:10.1016/j.visinf.2017.01.005 描述 碩士
國立政治大學
圖書資訊與檔案學研究所
107155019資料來源 http://thesis.lib.nccu.edu.tw/record/#G0107155019 資料類型 thesis dc.contributor.advisor 陳志銘 zh_TW dc.contributor.advisor Chen, Chih-Ming en_US dc.contributor.author (Authors) 何偲佑 zh_TW dc.contributor.author (Authors) Ho, Szu-Yu en_US dc.creator (作者) 何偲佑 zh_TW dc.creator (作者) Ho, Szu-Yu en_US dc.date (日期) 2020 en_US dc.date.accessioned 3-Aug-2020 17:50:50 (UTC+8) - dc.date.available 3-Aug-2020 17:50:50 (UTC+8) - dc.date.issued (上傳時間) 3-Aug-2020 17:50:50 (UTC+8) - dc.identifier (Other Identifiers) G0107155019 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/131073 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 圖書資訊與檔案學研究所 zh_TW dc.description (描述) 107155019 zh_TW dc.description.abstract (摘要) 本研究旨在開發支援數位人文研究之「階層式主題分析工具」，能輔助人文學者，將具時間戳記的相關文本劃分為多個時期，依據各時期之文本進行階層式主題建模，建立一棵屬於該時期、具有樹狀結構之階層式主題模型樹，再透過視覺化的方式呈現，從而輔助人文學者進行文本遠讀分析。同時，亦提供「比較網絡圖」功能，可針對使用者所劃分的時期區段，提供兩個時期之階層主題網絡圖比較，以輔助使用者進行擬探索主題之差異比較，並追蹤特定觀點下的主題概念如何隨著時間而進行變化，進而對文本主題的整體脈絡有更全面的認識。此外，也提供使用者查看來源文本資料的功能，以達到整合細讀和遠讀的輔助主題探索功能。為了驗證此一工具對於支援數位人文研究的效益，本研究以實驗研究法之對抗平衡設計比較實驗對象依序使用有無「階層式主題分析工具」之「羅家倫先生文存數位人文平台」進行文本探索，在所填寫之主題探索評估表得分與探索出相關主題數量與時間上，是否具有顯著的差異；並以科技接受度問卷、半結構訪談的方式瞭解實驗對象對「階層式主題分析工具」的看法與感受；最後，透過滯後序列分析搭配螢幕錄影分析，探討實驗對象操作兩個不同工具的使用行為轉移。實驗結果發現，實驗對象採用具階層式主題分析工具之「羅家倫先生文存數位人文平台」，更能輔助其在短時間內掌握特定觀點下感興趣的文本主題脈絡，並啟發進一步探索之方向。此外，從滯後序列分析結果發現，具階層式主題分析工具之「羅家倫先生文存數位人文平台」所提供之主題詞彙較能符合使用者之期待與需求，並引導使用者連結至相關聯之文本進行閱讀，使其有效與細讀功能進行鏈結。在科技接受度分析與訪談資料分析部分可得知，實驗對象對於具「階層式主題分析工具」之「羅家倫先生文存數位人文平台」持高度正面肯定態度，認為此一工具能輔助其於短時間內掌握特定觀點之主題脈絡與主題內容。但是，認為工具提供之關聯性文本的數量以及萃取出之主題詞彙的精確性仍有進一步改善之空間。在未來研究方向上，可將本工具應用至解讀羅家倫文存以外之其他數位人文領域，探討其帶來之輔助主題脈絡探索效益、亦或嘗試不同主題模型之演算法，以探討不同主題模型支援主題分析的適用性。 zh_TW dc.description.abstract (摘要) This research aims to develop a "Hierarchical Topic Analysis Tool", for supporting research on digital humanities, allowing humanists dividing related texts with time stamp into several periods, and perform hierarchical topic modeling based on the text of each period. The tool will build a hierarchical topic model tree with tree structure belonging to the period, and then present it visually to assist the humanists in the analysis of text distance reading. Meanwhile, "Comparison Network Map" function is provided for assisting users to compare the hierarchical topic network map of the two periods according to the two periods divided by the user. Users are able to compare the differences between the topics they want to explore, and to track how the concept of the topic under a specific viewpoint changes over time, so as to understand the overall context of text topic more comprehensive. In addition, "view source text" function is provided for assisting users to explore topic by combining close reading and distance reading. To verify the effectiveness of "Hierarchical Topic Analysis Tool" in supporting digital humanities research, counterbalanced design in quasi-experimental research is applied in this study to compare the research subjects with and without "Hierarchical Topic Analysis Tool" in Mr. Lo Chia-lun`s Works Digital Humanities Research Platform for text exploration, and if there were significant differences in the score of Topic Explore Form, quantity of exploring related topic and exploring time. Technology acceptance questionnaire and semi-structured interview are utilized for understanding the research subjects’ opinions and perception of “Hierarchical Topic Analysis Tool”. Finally, lag sequential analysis and screen recording analysis are used for observing the research subjects’ behavior processes using two different systems to discuss the notable difference in the operation behavior transfer.The experimental results show that the research subjects who used the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform with "Hierarchical Topic Analysis Tool" could grasp better in the context of the text topic of interest from a specific viewpoint at short notice, and inspire the direction of further exploration than the research subjects who used the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform without "Hierarchical Topic Analysis Tool." Moreover, lag sequential analysis reveals that the topic vocabulary provided by the Mr. Lo Chia-lun`s Works Digital Humanities Research Platform with "Hierarchical Topic Analysis Tool" can accord with the demands of user better. The user is guided to link to the related texts for reading, so that it is able to combine with "close reading" function more effectively. The technology acceptance and interview data analysis reveal highly positive perception of the research subjects on “Hierarchical Topic Analysis Tool”. It presents that such a tool could rapidly assist them grasp the context of topic from a specific viewpoint and content of topic. However, the quantity of related text provided by "Hierarchical Topic Analysis Tool" and accuracy of topic vocabulary still require further improvement. In the future directions, the tool could be used to analyze the other fields of text to discuss the benefit of supporting the users to explore the context of topic, and attempt to apply different algorithms of topic model to compare the applicability of topic model with the one used in the present study. en_US dc.description.tableofcontents 第一章 緒論 1第一節 研究背景與動機 1第二節 研究目的 4第三節 研究問題 5第四節 研究範圍與限制 6第五節 名詞解釋 7第二章 文獻探討 10第一節 數位人文 10第二節 主題建模 13第三節 羅家倫先生研究 16第三章 系統設計 19第一節 系統設計理念 19第二節 系統架構 21第三節 系統元件 24第四節 系統開發環境 28第五節 系統介面與功能 29第四章 研究設計與實施 34第一節 研究架構 34第二節 研究方法 38第三節 研究對象 39第四節 研究工具 39第五節 實驗設計 43第六節 資料與分析 46第七節 研究實施步驟 48第五章 實驗結果分析 50第一節 實驗對象基本資料分析 51第二節 有無階層式主題分析工具之「羅家倫先生文存數位人文平台」使用成效分析 53第三節 有無階層式主題分析工具之「羅家倫先生文存數位人文平台」探索主題數量差異分析 54第四節 有無階層式主題分析工具之「羅家倫先生文存數位人文平台」探索主題時間差異分析 56第五節 有無階層式主題分析工具之「羅家倫先生文存數位人文平台」使用者科技接受度差異分析 57第六節 有無階層式主題分析工具之「羅家倫先生文存數位人文平台」使用者行為歷程分析 59第七節 訪談資料分析 71第八節 系統使用案例 85第九節 綜合討論 88第六章 結論與建議 93第一節 結論 93第二節 工具改善建議 97第三節 未來研究方向 99參考文獻 101附錄一 受試者參與研究同意書 105附錄二 羅家倫先生文存之「文學觀點」主題探索評估表 106附錄三 羅家倫先生文存之「新文化觀點」主題探索評估表 107附錄四「具階層式主題分析工具」科技接受度 108附錄五「無階層式主題分析工具」科技接受度 109附錄六「具階層式主題分析工具」訪談大綱 110附錄七「無階層式主題分析工具」訪談大綱 112 zh_TW dc.format.extent 4288104 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0107155019 en_US dc.subject (關鍵詞) 數位人文 zh_TW dc.subject (關鍵詞) 主題分析 zh_TW dc.subject (關鍵詞) 階層主題建模 zh_TW dc.subject (關鍵詞) 文本探勘 zh_TW dc.subject (關鍵詞) 資訊視覺化 zh_TW dc.subject (關鍵詞) 滯後序列分析 zh_TW dc.subject (關鍵詞) Digital humanities en_US dc.subject (關鍵詞) Topic analysis en_US dc.subject (關鍵詞) Hierarchical topic modeling en_US dc.subject (關鍵詞) Text mining en_US dc.subject (關鍵詞) Information visualization en_US dc.subject (關鍵詞) Lag sequential analysis en_US dc.title (題名) 數位人文研究平台之階層式主題分析工具發展與應用 zh_TW dc.title (題名) Development and Application of Digital Humanities Research Platform with Hierarchical Topic Analysis Tool en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) 中文文獻中國哲學書電子化計劃(2019)。中國哲學書電子化計劃。上網日期：108年12月20日，檢自：https://ctext.org/zh史雲波(2009)。羅家倫的"五四"觀及其歷史演變。天津社會科學，4(4)，134-137。杜協昌(2018)。DocuSky 與文本字詞關聯圖的視覺化應用。「第九屆數位典藏與數位人文國際研討會」發表之論文，法鼓文理學院。邱偉雲(2019)。主題模型與歷史記憶:數字人文視野下數字記憶史研究理論方法芻議。「文本探勘˙圖像標記-數位工具與人文詮釋國際工作坊」發表之論文，華人文化主體性研究中心。洪瑞嶸(2011)。階層式主題與句子之貝氏非參數模型。國立成功大學資訊工程學系碩博士班碩士論文。粘慈卿(2018)。羅家倫校長學之研究。國立中興大學教師專業發展研究所碩士論文。許小青(2005)。羅家倫與抗戰前的中央大學(1932-1937)。近代中國，163，158-184。郭海俠(2014)。“五四”命名者羅家倫的教育理念與行動。蘭台世界，28，12-13。陳光華、薛弼心(2015)。數位人文研究的在地特性與全球特性之探討。人文與社會科學簡訊，17:1，83-88。陳志銘、林正和(2019)。數位人文研究平台之觀點變遷和年代劃分工具發展與應用。「第十屆數位典藏與數位人文國際研討會」發表之論文。陳奕安(2016)。適用於中文史料文本之標記式主題模型分析方法研究。國立政治大學資訊科學系碩士論文。陳春生(1985)。新文化的旗手:羅家倫傳。近代中國出版社。項潔、涂豐恩(2011)。導論――什麼是數位人文。載於項潔(主編)，從保存到創造: 開啟數位人文研究(9-28頁)。臺北市：國立臺灣大學出版中心。馮夏根(2006)。羅家倫與中國近代史研究。信陽師範學院學報（哲學社會科學版），26(3)，122-124。趙尚杰(2010)。羅家倫高等教育思想研究。中國近現代教育史，8，12-13。趙寧(2016)。簡述羅家倫對近代史料的搜集保存。才智，8，194-195。蕭勝文(2000)。羅家倫與中央大學發展之研究（1932-1941）。國立臺灣師範大學歷史研究所碩士論文。謝曉欣(2015)。教育家羅家倫及其高等教育思想研究。當代教育實踐與教學研究，8，43-44。英文文獻Alencar, A. B., de Oliveira, M. C. F., & Paulovich, F. V. (2012). Seeing beyond reading: a survey on visual text analytics. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(6), 476–492. doi:10.1002/widm.1071Analytics Tools & Solutions for Your Business - Google Analytics (n.d.). Retrieved December 20, 2019, from https://marketingplatform.google.com/about/analytics/Bakeman, R., & Gottman, J. M. (1997). Observing interaction: An introduction to sequential analysis, 2nd ed. New York: Cambridge University Press. doi:10.1017/CBO9780511527685Berry, D. (2012). Understanding digital humanities. Springer.Blei D., Ng A., & Jordan M. (2003). Latent dirichlet allocation. The Journal of Machine Learning Research, 3,993-1022.Blei, D. M., Griffiths, T. L., & Jordan, M. I. (2010). The nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies. Journal of the ACM, 57(2), 1-30. doi:10.1145/1667053.1667056Boyles, N. (2013). Closing in on close reading. Educational Leadership,70(4), 36–41.Chen, C. M. & Chang, C. (2019). A Chinese ancient book digital humanities research platform to support digital humanities research. The Electronic Library, 37(2), 314-336.Chen, C. M., Chen, Y. T., & Liu, C. Y. (2019). Development and evaluation of an automatic text annotation system for supporting digital humanities research. Library Hi Tech, 37(3), 436-455.Chen, P., Zhang, N. L., Liu, T., Poon, L. K. M., Chen, Z., & Khawar, F. (2017). Latent tree models for hierarchical topic detection. Artificial Intelligence, 250, 105-124. doi:10.1016/j.artint.2017.06.004Drucker, J. (2013), “Intro to digital humanities: Introduction”, UCLA Center for Digital Humanities. Web available at http://dh101.humanities.ucla.edu/?page_id=13, Retrieved January 28, 2018.Haldar, R., Mukhopadhyay D. (2011). Levenshtein distance technique in dictionary lookup methods: An improved approach. Retrieved from http://arxiv.org/abs/1101.1232Hockey, S. (2004). The history of humanities computing. In R. Siemens & S. Schreibman(Eds.), A Companion to Digital Humanities. Retrieved from http://www.digitalhumanities.org/companion/Hofmann, T. (1999). Probabilistic latent semantic indexing. Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR ’99, 50-57. doi:10.1145/312624.312649Hwang, G.-J., Yang, L.-H., & Wang, S.-Y. (2013). A concept map-embedded educational computer game for improving students’ learning performance in natural science courses. Computers & Education, 69, 121-130.Jänicke, S., Franzini, G., Cheema, M. F., & Scheuermann, G. (2017). Visual text analysis in digital humanities: Visual text analysis in digital humanities. Computer Graphics Forum, 36(6), 226-250. doi:10.1111/cgf.12873Li, Z., Tang, J., Wang, X., Liu, J., & Lu, H. (2016). Multimedia news summarization in search. ACM Transactions on Intelligent Systems and Technology, 7(3), 1–20. doi:10.1145/2822907Liu, T., Zhang, N. L., & Chen, P. (2014). Hierarchical latent tree analysis for topic detection. In T. Calders, F. Esposito, E. Hüllermeier, & R. Meo (Eds.), Machine Learning and Knowledge Discovery in Databases (Vol. 8725, pp. 256-272). Berlin, Heidelberg: Springer Berlin Heidelberg. doi:10.1007/978-3-662-44851-9_17MORETTI, F. (2005). Graphs, Maps, Trees: Abstract Models for a Literary History. Verso, London and New York.Moretti, G., Sprugnoli, R., Menini, S., & Tonelli, S. (2016). ALCIDE: Extracting and visualising content from large document collections to support humanities studies. Knowledge-Based Systems, 111, 100-112.Papadimitriou, C. H., Tamaki, H., Raghavan, P., & Vempala, S. (1998). Latent semantic indexing. Proceedings of the Seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems - PODS ’98, 159-168. doi:10.1145/275487.275505Rosenzweig, R. (2003). Scarcity or abundance? Preserving the past in a digital era. The American Historical Review, 108(3), 735–762.Stommel, M. & Wills, C.E.(2004). Clinical research: concepts and principles for advanced practice nurses. Philadelphia, Pa.; London: Lippincott Williams & Wilkins.Wei, F., Liu, S., Song, Y., Pan, S., Zhou, M. X., Qian, W., … Zhang, Q. (2010). TIARA: A visual exploratory text analytic system. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining - KDD ’10,153-162. doi:10.1145/1835804.1835827Cui, W., Liu, S., Tan, L., Shi, C., Song, Y., Gao, Z., …Qu, H. (2011). TextFlow: Towards Better Understanding of Evolving Topics in Text. IEEE Transactions on Visualization and Computer Graphics, 17(12), 2412-2421. doi:10.1109/TVCG.2011.239Yang, Y., Yao, Q., & Qu, H. (2017). VISTopic: A visual analytics system for making sense of large document collections using hierarchical topic modeling. Visual Informatics , 1(1), 40-47. doi:10.1016/j.visinf.2017.01.005 zh_TW dc.identifier.doi (DOI) 10.6814/NCCU202001137 en_US
