臺灣博碩士論文加值系統

隨著文字資訊的爆炸式增長，越來越多的訊息開始以電子文本的形式儲存及傳遞。但隨著文本內容資訊量不斷地增加，使用者也越來越難以快速地掌握文本全貌。因此本研究試圖透過主題模型（TopicModels）、標記式主題模型（Labeled Topic Models）演算法－在自然語言處理領域裡文本探勘的方法，識別出大規模文本中潛藏的主題訊
息之後，再利用圖像視覺化在資訊表達上的優勢和效率，透過各種視覺化圖案的呈現從不同的角度來探索文本，形成一種嶄新的大規模文本閱讀與分析方式。

本研究設計了兩階段實驗：第一階段任務導向性實驗、第二階段指定任務實驗，以及評估問卷來驗證本介面的易用性（ Ease-of-use ）和有用性（ Usefulness ）。並透過實驗問卷的分數結果驗證了，本研究所設計之介面在實務上的確能輔助專家學者進行文本相關研究，也能
讓對文本熟悉程度不一的使用者在利用此介面探索文本的過程中，更快速地掌握大規模文本的事件全貌。

With the explosion of text information, there are more and more data being recorded and transmitted in the form of texts. However, as the amount of textual information becomes larger, how to effectively and efficiently realize the information also becomes more difficult. This study attempts to use the Topics Models, text-mining techniques to identify the important topics in the large textual information. In addition, this study also aims to use the techniques of data visualization to present the most informative and valuable details within the large texts.

There are two parts in this work: the first part is the introduction of text mining algorithms and the second part is the design of the data visualization.Moreover, in the experiments, we also conduct several surveys to verify the proficiency and usefulness and the visualization design. The results of the experiments and surveys, supports that our design provides an effective and efficient interface for users to understand a large set of texts, even for the experts familiar with the corpus.

第一章緒論. . . . . . . 1
1.1 前言. . . . . .. . 1
1.2 研究動機. . . . . . 1
1.3 研究目的. . . . . . 2
1.4 論文架構. . . . . . 3
第二章相關文獻探討. . . . 4
2.1 主題模型. . . . . . 4
2.1.1 隱含狄利克雷分布LDA . . . . . . . . . 5
2.1.2 標記式隱含狄利克雷分布Labeled LDA . .. 5
2.2 主題模型視覺化. . . . . . . . 6
2.2.1 靜態主題模型視覺化展示. . . . . . .. 7
2.2.2 靜態主題模型視覺化總結. . . . . . . . 9
第三章介面概念與設計. . . . . . . . . . . 10
3.1 系統概念. . . . . . 10
3.1.1 文本主題與關鍵字. . . . . . . . . . 12
3.2 介面設計流程. . . . . . . . . .. . . 14
3.3 系統介面. . . . . . 15
3.3.1 首頁（Index） . . . . . . . . . 16
3.3.2 主題／主題代表字總覽（Grid） . . . 18
3.3.3 主題遠近分佈（Scaled） . . .. .. . 18
3.3.4 主題列表（List） . . . . . . .. . 19
3.3.5 主題年代分布（Year） . . . . .. . 20
3.3.6 文字索引（Index） . . . . . . . . 20
3.3.7 主題專題頁（Topic） . . . . .. . 21
3.3.8 詞彙搜尋頁面（Search） . . . . . 21
3.4 介面設計總結. . . . . . . . . . 22
第四章介面實作技術. . . . . . 23
4.1 整體介面架構. . . . . . . . . . 23
4.1.1 整體顏色設計. . . . . . . . . 23
4.2 視覺化圖表技術說明. . . . . . . 24
4.2.1 各式主題模型視覺化技術呈現. . .. 25
4.2.2 其餘靜態圖表技術. . . . . . . 29
4.3 文本主題遠近分析技術. . . .. . .. 30
第五章實驗設計與結果評估. . . . . . . 33
5.1 實驗目的. . . . . . 33
5.2 實驗對象. . . . . . 33
5.3 實驗流程. . . . . . 34
5.3.1 實驗前測問卷. . . . . . . . 35
5.3.2 前置介面引導任務. . . . . . 36
5.3.3 第一階段易用性調查問卷. . . . 37
5.3.4 第二階段指定任務. . . . .. . 38
5.3.5 第二階段有用性調查問卷. . . . 39
5.4 實驗結果分析與討論. . . . . . . 41
5.4.1 系統可用性尺度量表（SUS）比較結果分析. . 41
5.4.2 第二階段有用性問卷內容結果分析. . . . . 44
5.4.3 實驗前測問卷前後結果分析. . . . . . 47
5.4.4 開放式問題訪談結果分析. . . . . 52
第六章結論與未來展望. . . . . . . 54
6.1 研究結論. . . . . . 54
6.2 未來發展與改進. . . . . . . . . 54
參考文獻. . . . . . . . . . . . . . 55
附錄. . . . . . . . . . . . . . . 58
附錄一第一階段介面引導任務問題列表. . ..58
附錄二受測者開放性問題回饋. . .. . .. 60

[1] W. Albert and T. Tullis. Measuring the user experience: collecting, analyzing, and presenting usability metrics. Newnes, 2013.
[2] A. Bangor, P. Kortum, and J. Miller. Determining what individual sus scores mean: Adding an adjective rating scale. Journal of usability studies, 4(3):114–123, 2009.
[3] D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent dirichlet allocation. the Journal of machine Learning research, 3:993–1022, 2003.
[4] M. Bostock. D3. js. Data Driven Documents, 492, 2012.
[5] A. J.-B. Chaney and D. M. Blei. Visualizing topic models. 2012.
[6] J. Chuang, C. D. Manning, and J. Heer. Termite: Visualization techniques for assessing textual topic models. In Proceedings of the International Working Conference on Advanced Visual Interfaces, pages 74–77. ACM, 2012.
[7] D. Cochran. Twitter Bootstrap Web Development How-To. Packt Publishing Ltd, 2012.
[8] S. T. Dumais. Latent semantic analysis. Annual review of information science and technology, 38(1):188–230, 2004.
[9] S. Eppinger and K. Ulrich. Product design and development. McGraw-Hill Higher Education, 2015.
[10] K. Finstad. The system usability scale and non-native english speakers. Journal of usability studies, 1(4):185–188, 2006.
[11] T. Hofmann. Probabilistic latent semantic indexing. In Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrieval, pages 50–57. ACM, 1999.
[12] P. Legris, J. Ingham, and P. Collerette. Why do people use information technology? a critical review of the technology acceptance model. Information & management, 40(3):191–204, 2003.
[13] R. Likert. A technique for the measurement of attitudes. Archives of psychology, 1932.
[14] J. Murdock and C. Allen. Visualization techniques for topic model checking. In AAAI, pages 4284–4285, 2015.
[15] J. Nielsen and T. K. Landauer. A mathematical model of the finding of usability problems. In Proceedings of the INTERACT’93 and CHI’93 conference on Human factors in computing systems, pages 206–213. ACM, 1993.
[16] D. Ramage, D. Hall, R. Nallapati, and C. D. Manning. Labeled lda: A supervised topic model for credit attribution in multi-labeled corpora. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1-Volume 1, pages 248–256. Association for Computational Linguistics, 2009.
[17] M. Rosen-Zvi, T. Griffiths, M. Steyvers, and P. Smyth. The author-topic model for authors and documents. In Proceedings of the 20th conference on Uncertainty in artificial intelligence, pages 487–494. AUAI Press, 2004.
[18] I. J. Schoenberg. Cardinal spline interpolation. SIAM, 1973.
[19] B. H. Sheppard, J. Hartwick, and P. R. Warshaw. The theory of reasoned action: A meta-analysis of past research with recommendations for modifications and future research. Journal of consumer research, 15(3):325–343, 1988.
[20] C. Sievert and K. E. Shirley. Ldavis: A method for visualizing and interpreting topics. 2014.
[21] Y. W. Teh, M. I. Jordan, M. J. Beal, and D. M. Blei. Sharing clusters among related groups: Hierarchical dirichlet processes. In NIPS, pages 1385–1392, 2004.
[22] Y.W. Teh, M. I. Jordan, M. J. Beal, and D. M. Blei. Hierarchical dirichlet processes. Journal of the american statistical association, 2012.
[23] S. Wold, K. Esbensen, and P. Geladi. Principal component analysis. Chemometrics and intelligent laboratory systems, 2(1-3):37–52, 1987.
[24] N. Yau. Data points: Visualization that means something. JohnWiley & Sons, 2013.
[25] 賈西平, 彭宏, 鄭啟倫, 石時需, and 江焯林. 基于主題的文檔檢索模型. 華南理工大學學報(自然科學版), 36(9):37–42, 2008.