本論文主要目的在實現一套可完全經由語意訊息擷取出情緒類別之系統。將語言學的資訊加入情緒研究的領域大多挶限於情緒關鍵字使用及人工定義的情緒規則，但不論何種皆有其缺點。首先，情緒關鍵字的使用雖然有助於情緒辨識的正確率，但情緒關鍵字的建立僅是語言學上最淺顯的資訊，並無法完整表達其它語言學上較深層的資訊如文句語意等。再者，由人工定義的情緒規則，由於領域的改變，情緒規則也就跟著改變，須由這領域的專家再依需要由人工定義規則，所花費的人力與時間均相當龐大。而且當應用領域改變時，所有的工作又需全部從頭再建立一次，非常不具可移植性。因此本系統的研究發展上，均以能克服上述兩項缺點為考量，建立一個能分析文句語意內容，並具有可移植性的系統架構。
本論文首先參考有關情緒及情緒心理學相關研究，歸納能引發情緒的基本因素。再以知網 (HowNet) 與中研院中文詞知識庫小組的中文詞類分析技術報告為參考資料，定義了在一般語言上與領域無關且表達某些特定語意的語意標籤 (semantic label)。接著以語意標籤為中心，擷取語句中另外表達附屬語意的詞，經由知網的擴充，將語句中的語意均擷取出之後，運用資料探勘(data mining)的技術，自動由訓練語料中生成情緒規則。最後利用自動生成的的情緒規則將語句化為向量空間，再利用分類的技術，訓練出一情緒分類模組，最後由此情緒分類模組可將語句表達的情緒分類。
本系統經實驗結果，對於原設計領域之語料可達到八成之辨識率，同時對於任意語料經訓練後，也可達到約六成的辨識率。此結果說明本系統中由於語意標籤的使用及自動情緒規則的生成，已可達到初步領域無關的普遍性及領域調整的適應性，同時也可達到語意內涵的初步理解。

This thesis presents an emotion classification system based on semantic content analysis. So far the linguistics based emotion extraction systems usually deal with emotional keywords or manually defined emotional rules and also have some disadvantages. Firstly, though the utilization of emotional keywords is useful for the increase of the classification accuracy, it uses only part of the linguistic information. A system with only keyword information cannot take into account the deep information of linguistics, such as semantic meaning. Secondly, the rules defined manually strongly depend on the application domain. As domain changes, rules have to be re-defined by some domain experts manually. This makes the construction of the system time consuming and un-portable. The system proposed in this thesis tends to solve these two problems.
We first reduce the basic rules that can explain the essential of emotion generation from the literatures in emotion psychology. According to the linguistic definition, such as HowNet and CKIP, we define some domain independent semantic labels. With the help of HowNet, we can extract the semantic meaning of an input sentence by these semantic labels and transfer it to semantic transactions. The data mining technique is then applied to generate the emotional rules from these semantic transactions automatically. Finally, compared to the emotional rules, the semantic transactions are mapped to a vector space and used to train the SVM classification models.
In the experiment, the classification accuracy was achieved at 80% for the original collected corpus. It can also achieved about 60% for other corpus. From the experimental results, the performance of semantic label and automatic rule generation is promising. And the system can essentially satisfy the requirement for domain portability.

[1] V.Kostov, S.Fukuda, “Emotion in User Interface,Voice Interaction System,” IEEE ,pp. 798~803, 2000.
[2] Feng Yu, Eric Chang, Ying-Qing Xu, Heung-Yeung Shum, “Emotion Detection from Speech to Enrich Multimedia Content,” Advances in Multimedia Information Processing, PCM ,pp. 550~557,2001.
[3] Joy Nicholson, Kazuhiko Takahashi, Ryohei Nakatsu, “Emotion Recognition in Speech Using Neural Networks,” IEEE ,pp. 495~501, 1999.
[4] Tin Lay New,Foo Say Wei, Liyanage C De Silva, ”Speech Based Emotion Classification,” IEEE Transaction on Speech and Audio Processing ,pp. 297~301, 2001.
[5] Frank Dellaert, Thomas Polzin, Alex Waibel, ”Recognizing emotion in speech,” International Conference on Spoken Language Processing, CSLP ,1996.
[6] S.Fukuda, V. Kostov, “Extracting Emotion from Voice,” IEEE InternationalConference on Systems Man and Cybernetics, pp. 299~304, 1999.
[7] P. Ekman, “Facial Action Coding System(FACS),” Palo Alto:Consulting Psychology Press, 1978.
[8] Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn, ”Robst Lip Tracking by Combining Shape, Color and Motion,” Proc.Asian Conf. Computer Vision, pp. 1040~1045, 2000.
[9] Ying-li Tian, Takeo Kanade, Jeffrey F. Cohn, “Recognizing Action Units for Facial Expression Analysis, ” IEEE Transaction on Pattern Analysis and Machine Intelligence, pp. 97~115, 2001.
[10] Rui Liao ,Stan Z. Li, “Face Recognition Based on Multiple Facial Features,” IEEE Int. Conf. on Automatic Face and Gesture Recognition, pp. 1~6, 2000.
[11] D. Yang, T. Kunihiro, H. Shimoda, H. Yoshikawa, “A Study of Real-time Image Processing Method for Treating Human Emotion by Facial Expression,” IEEE , pp. 360~364, 1999.
[12] M.Pantic, L.J.M. Rothkrantz, ”An Expert System for Multiple Emotional Classification of Facial Expressions,” IEEE pp. 113~120, 1999.
[13] T. Otsuka, J. Ohya, ”Recognizing Multiple Person’s Facial Expressions Using HMM Based on Automatic Extraction of Significant Frames from Image Sequences,” Proc. Int. Conf. on Image Processing ,pp. 546~549, 1997.
[14] Liyanage C. De Silva, Tsutomu Miyasato, Ryohei Nakaatsu, “Facial Emotion Recognition Using Multi-model Information,” International Conference on Information, Communications and Signal Processing, IEEE ,pp. 397~401, 1997.
[15] Lawrence S. Chen, Thomas S.Huang, “Multimodel Human Emotion/Expression Recognition,” IEEE Int. Conf. On Automatic Face & Gesture Recognition, pp. 366~371, 1998.
[16] Liyanage C. De Silva, Pei Chi Ng, “Bimodel Emotion Recognition,” IEEE International Conference on Automatic Face and Gesture Recognition, pp. 332~335, 2000.
[17] L. S. Chen, H. Tao & T. S. Huang, T. Miyasato & R. Makatsu, “Emotion Recognition from Audiovisual Information,” IEEE Second Workshop on Multimedia Signal Processing, pp. 83~88, 1998.
[18] Jeffrey F. Cohn, Gray S. Katz, “Bimodal Expression of Emotion by Face and Voice,” ACM International Multimedia Conference, pp. 41~44, 1998.
[19] Chul-Min Lee, Shrikanth S. Narayanan, Roberto Pieraccini, “Combining Acoustic and Language Information for Emotion Recognition,” ICSLP 2002, 2002.
[20] Fiorella de Rosis, Floriana Grasso, A. M. Paiva (Ed.), “Affective Interactions,” LNAI 1814, pp. 204-218, 2000.
[21] 蔡秀玲, 楊智馨, “情緒管理,” 揚智出版社, 1999.
[22] Richard S. Lazarus, Bernice N. Lazarus, 李素卿譯, “Passion and Reason-Making Sense of Our Emotions，感性與理性-了解我們的情緒,” 五南圖書出版公司, 2001.
[23] “政戰幹部之情緒管理策略研究初探,” 政治作戰學校軍事社會科學研究中心, 1998.
[24] 瞿海源譯, “動機和情緒,” 教育部訓育委員會編.
[25] 中文詞知識庫小組, “中文詞類分析(三版)”, 中央研究院資訊科學研究所技術報告, 1993.
[26] Jiawei Han, Micheline Kamber, “Data Mining: Concepts and Techniques,” MORGAN KAUFMAMN PUBLISHERS, 2000.
[27] Valdimir Cherkassky, Filip Mulier, “Learning From Data,” 1998.
[28] Marti A. Hearst, “Support Vector Machine,” IEEE Intelligent Systems, pp.18~28, 1997.
[29] Ze-Jing Chuang, Chung-Hsien Wu, “Emotion Recognition from Textual Input using an Emotional Semantic Network,” ICSLP 2002, 2002.