在各式各樣的小說當中，隨著內容文字的變化，讀者的情緒也常常隨之起伏。而隨著每個作者用字遣詞習慣的不同，也會形成獨特的寫作風格，有些甚至會成為其他人爭相模仿的對象，進而形成引領當代作品的潮流等。而在這些小說當中，去除劇情的影響力外，作家使用的情緒字詞數量、頻率或是強烈程度等會連帶影響每個讀者閱讀該小說時情緒的起伏。對於作者來說，傳統文學小說在只有文字為媒介的情況下，如何操作所使用的不同字彙來牽引讀者情緒，進而找出暢銷作品的獨特套路，或是不同類型的作品可能使用的情緒引領手法也不太相同。
因此在本篇論文中，試著利用英國作查爾斯‧狄更斯的作品《遠大前程》作為分析之文本，以Plutchik的八個情緒作為基礎情緒進行計算，能夠比單純以正負項數值更準確地表達情緒的變化，而在使用文法規則加以規範，以章節為單位觀察文本作品的情緒流向變化，來了解使用情緒字詞數量、頻率或是強烈程度等所帶來的閱讀情緒起伏影響。

Readers who touched by the texts in various novels always exhibit mood swings. The choice of words made by different authors makes the writing style of the article unique. Some of the authors may even become a role model leading the contemporary trend. However, the amount of emotional words, its usage frequency and intensity may also affect every reader’s mind regardless of the plot. As for an author, there’s slightly difference between various types of literature for how to touch readers and make their piece of work a best-selling book.
Therefore, we are trying to analysis Charles Dickens’ fiction《Great Expectations》 for understanding the influence of emotional words, its usage frequency and intensity for readers based on calculating Plutchik’s eight basic emotions with grammar and observing the change of emotion flow in chapter, which is much precise on explaining emotional changes than simple calculation with positive and negative scores.

論文審定書 i
摘要 ii
ABSTRACT iii
目錄 iv
圖目錄 vii
表目錄 viii
1 緒論 1
1.1 研究背景與動機 1
1.2 研究問題 3
2 文獻探討 5
2.1 理論概念 5
2.1.1 Wheel of Emotion 5
2.1.2 Pointwise Mutual Information (PMI) 6
2.1.3 Sequence Alignment 6
2.2 情緒定義 7
2.3 情緒辨識技術的演進 8
2.4.1 情緒極性與類別法 Categorical Model 9
2.4.2 維度座標法 Dimensional Model 10
2.4 相似之情緒分析服務 11
2.5 潛在語意分析 Latent Semantic Analysis 15
3 研究方法 17
3.1 研究問題定義 17
3.1.1 情緒的分類方式與表達 17
3.1.2 各時代小說類型梗概 19
3.1.3 分析文本介紹 20
3.2 流程架構 20
3.3 字詞字句分析 21
3.3.1 情緒辭典Emotion Dictionary 21
3.3.2 Sentence-Level分析 23
3.4 語意分析 27
3.4.1 Latent Semantic Analysis (LSA) 27
3.5 作家寫作風格相似性計算 31
4 實驗與成果 32
4.1 情緒辨識方法準確度測量探討 32
4.1.1 實驗流程 32
4.1.2 實驗問卷 34
4.1.3 資料分析與整理 34
4.1.4 實驗組與對照組比較 35
4.1.5 精確度與準確度評估 37
4.2 作家寫作風格變化探討 46
4.3 實驗成果探討 52
4.3.1 實驗結果分析 52
4.3.2 導致實驗誤差的因素 54
5 結論 56
5.1 總結 56
5.2 研究限制 56
5.2.1 實驗受測者限制 56
5.2.2 系統限制 56
5.2.3 實驗章節限制 57
5.3 研究貢獻 57
5.4 未來展望 58
參考文獻 59

[1] Zhao, Jian, et al. "PEARL: An interactive visual analytic tool for understanding personal emotion style derived from social media." Visual Analytics Science and Technology (VAST), 2014 IEEE Conference on. IEEE, 2014.
[2] Quan, Changqin, and Fuji Ren. "Sentence emotion analysis and recognition based on emotion words using Ren-CECps." International Journal of Advanced Intelligence 2.1 (2010): 105-117.
[3] IU, Johan Bollen, and Huina Mao IU. "Twitter mood predicts the stock market." (2011).
[4] Aman, Saima, and Stan Szpakowicz. "Identifying expressions of emotion in text." Text, Speech and Dialogue. Springer Berlin Heidelberg, 2007.
[5] López, Juan Miguel, et al. "Towards an ontology for describing emotions."Emerging Technologies and Information Systems for the Knowledge Society. Springer Berlin Heidelberg, 2008. 96-104.
[6] Pak, Alexander, and Patrick Paroubek. "Twitter as a Corpus for Sentiment Analysis and Opinion Mining." LREc. Vol. 10. No. 2010. 2010.
[7] Strapparava, Carlo, and Alessandro Valitutti. "WordNet Affect: an Affective Extension of WordNet." LREC. Vol. 4. 2004.
[8] Wollmer, Martin, et al. "Youtube movie reviews: Sentiment analysis in an audio-visual context." Intelligent Systems, IEEE 28.3 (2013): 46-53.
[9] Plutchik, Robert. "A general psychoevolutionary theory of emotion." Theories of emotion 1 (1980).
[10] Lehrer, Adrienne. "Semantic fields and lexical structure." (1974).
[11] Mohammad, Saif, Cody Dunne, and Bonnie Dorr. "Generating high-coverage semantic orientation lexicons from overtly marked words and a thesaurus." Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 2-Volume 2. Association for Computational Linguistics, 2009.
[12] Turney, Peter D., and Michael L. Littman. "Measuring praise and criticism: Inference of semantic orientation from association." ACM Transactions on Information Systems (TOIS) 21.4 (2003): 315-346.
[13] http://text-processing.com/demo/sentiment/ (2016/03/02)
[14] http://www.danielsoper.com/sentimentanalysis/ (2016/03/02)
[15] Stone, Philip, et al. "The general inquirer: A computer approach to content analysis." Journal of Regional Science 8.1 (1968): 113-116.
[16] Mohammad, Saif M. "From once upon a time to happily ever after: Tracking emotions in mail and books." Decision Support Systems 53.4 (2012): 730-741.
[17] Manis, Christine, and Steven Swann Jones. "The Fairy Tale: The Magic Mirror of the Imagination." (2005): 69-71.
[18] Mohammad, Saif M., and Peter D. Turney. Nrc emotion lexicon. NRC Technical Report, 2013.
[19] Picard, Rosalind W., and Roalind Picard. Affective computing. Vol. 252. Cambridge: MIT press, 1997.
[20] Bradley, Margaret M., and Peter J. Lang. Affective norms for English words (ANEW): Instruction manual and affective ratings. Technical Report C-1, The Center for Research in Psychophysiology, University of Florida, 1999.
[21] Ekman, Paul. "Facial expression and emotion." American psychologist 48.4 (1993): 384.
[22] Kennedy, Alistair, and Diana Inkpen. "Sentiment classification of movie reviews using contextual valence shifters." Computational intelligence 22.2 (2006): 110-125.
[23] Thayer, Robert E. The biopsychology of mood and arousal. Oxford University Press, 1990.
[24] https://tone-analyzer-demo.mybluemix.net/ (2016/03/02)
[25] http://nlp.stanford.edu:8080/sentiment/rntnDemo.html (2016/03/02)
[26] Fernández-Tobías, Ignacio, Iván Cantador, and Laura Plaza. "An emotion dimensional model based on social tags: Crossing folksonomies and enhancing recommendations." E-Commerce and Web Technologies. Springer Berlin Heidelberg, 2013. 88-100.
[27] Schuller, Björn, Gerhard Rigoll, and Manfred Lang. "Hidden Markov model-based speech emotion recognition." Acoustics, Speech, and Signal Processing, 2003. Proceedings.(ICASSP'03). 2003 IEEE International Conference on. Vol. 2. IEEE, 2003.
[28] Xie B. Research on key issues of Mandarin speech emotion recognition [Ph.D. Thesis]. Hangzhou: Zhejiang University, 2006
[29] Tyagi, Atul, and Nidhi Chandra. "A Proposed Approach with Analysis of Speech Signals for Sentiment Detection." Communication Systems and Network Technologies (CSNT), 2015 Fifth International Conference on. IEEE, 2015.
[30] Athar, Atifa, et al. "A fuzzy inference system for synergy estimation of simultaneous emotion dynamics in agents." Int. J. Sci. Eng. Res 2.6 (2011): 35-41.
[31] Asawa, Krishna, Vikrant Verma, and Surbhi Dhupar. "Emotion Analysis of the Text Using Fuzzy Affect Typing over Emotions." Context-Aware Systems and Applications. Springer Berlin Heidelberg, 2013. 249-257.
[32] Brooke, Julian. A semantic approach to automated text sentiment analysis. Diss. Simon Fraser University, 2009.
[33] Landauer, Thomas K., Peter W. Foltz, and Darrell Laham. "An introduction to latent semantic analysis." Discourse processes 25.2-3 (1998): 259-284.
[34] http://www.theatlantic.com/technology/archive/2016/07/the-six-main-arcs-in-storytelling-identified-by-a-computer/490733/ (2016/09/15)
[35] HALLSMAR, FREDRIK, and JONAS PALM. "Multi-class Sentiment Classification on Twitter using an Emoji Training Heuristic."
[36] Read, Jonathon. "Using emoticons to reduce dependency in machine learning techniques for sentiment classification." Proceedings of the ACL student research workshop. Association for Computational Linguistics, 2005.
[37] Chuang, Ze-Jing, and Chung-Hsien Wu. "Multi-modal emotion recognition from speech and text." Computational Linguistics and Chinese Language Processing 9.2 (2004): 45-62.
[38] Lin, Chenghua, and Yulan He. "Joint sentiment/topic model for sentiment analysis." Proceedings of the 18th ACM conference on Information and knowledge management. ACM, 2009.
[39] Maas, Andrew L., et al. "Learning word vectors for sentiment analysis." Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies-Volume 1. Association for Computational Linguistics, 2011.
[40] Wang, Lan, and Yuan Wan. "Sentiment classification of documents based on latent semantic analysis." Advanced research on computer education, simulation and modeling. Springer Berlin Heidelberg, 2011. 356-361.
[41] Gong, Yihong, and Xin Liu. "Generic text summarization using relevance measure and latent semantic analysis." Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval. ACM, 2001.
[42] Řehůřek, Radim, and Petr Sojka. "Gensim—Statistical Semantics in Python." (2011).