在衡量老師的教學內容或上課方式，一直以來都是透過在學期末發放課程問卷，老師收到意見回饋後，從中了解學生遇到的問題，便可以改善下次開課的教學內容，但是透過這樣的方式，無法立即幫助到本學期遇到問題的學生，因為課程問卷是屬於總結性的，要等到課程結束才能知道學生的意見回饋，無法立即的改善學生的問題，也無法在每次上課後都施測一次問卷，這樣會造成調查結果效度降低。
本研究提出利用意見探勘的方式，來對大學生的課堂學習動機做預測，這樣的方式可以結合學習社群平台裡討論區的功能來做分析，能讓老師立即的知道課堂上學生的學習動機。但在有關文本探勘上，中文和其他語言相比有著斷詞的困難，本研究使用兩種斷詞的方法：中研院斷詞(CKIP)和結巴斷詞(Jieba)，再利用詞頻來統計意見特徵值，TF-IDF(Term Frequency-Inverse Document Frequency)做為權重，完成整個資料處理的動作。
本研究透過Rapid Miner，一種在資料探勘領域的常用軟體，使用SVM(Support vector machine)來完成預測分類，在一開始的特徵選取上，除了詞頻之外還加入了詞性標註，但是出來的預測準確率只有50%左右，我們從這次實驗發現到是因為我們的特徵矩陣過大，所以我們利用關鍵字提取的方式，找到意見的常用辭彙，利用這些辭彙把原先的特徵做同義詞替換，達到縮減矩陣和集中特徵，使得預測準確率達68%，之後我們認為詞頻的方式無法好好的表現出字與字之間的關係，所以我們利用Stanford dependency parser又加入相依性語法(dependency grammar)做為新特徵加入，使得預測準確率達到了78%。

In a measure of the teacher's teaching content or teaching way are issued through course evaluation questionnaires at the end of the semester. After teacher received feedback, teacher can understand the problems that students have. Teacher can improve the course. However, through this way, it cannot help to students at this semester immediately. Because the course is a summative evaluation, until the end of the course the student feedback to be known. It is not immediately improve the students' questions. Because it will be reducing the validity of the findings, it cannot repeatedly issue the questionnaire.
This research proposes is to use opinion mining to make predictions learning motivation of college students. This way can combine the forum of learning community platform. It can allow teacher immediately knows student learning motivation. However, in the text mining, the tokenization of Chinese text is very difficult. This research uses two methods tokenization： CKIP and Jieba. Using the term frequency to count opinions eigenvalues.
In the beginning of the feature selection, in addition to the term frequency we also joined the part of speech tagging. But the prediction accuracy rate of only 50%. We use the keyword extraction to find common vocabulary about opinion. We use these words to replace original features by synonym for reducing the matrix and focusing feature. It makes the prediction accuracy rate of 68%. We consider term frequency cannot show the relationship between the word and the word. So we use the Stanford dependency parser to add dependency grammar as a new feature was added in feature matrix. It making the prediction accuracy rate of 78%.

吳鑑峰（民91）。應用語音及臉部表情之雙模態情緒辨識。國立成功大學博士論文，台南市。
洪紹祥（民100）。以虛擬化技術開發應用於私有雲服務之旅遊資訊分類推薦系統。南台科技大學碩士論文，台南市。
曾元顯（民101）。詞袋模型。取自：http：//terms.naer.edu.tw/detail/1679006/?index=1
連曉霧（民101）。開放式問題。取自：http://wiki.mbalib.com/zh-tw/%E5%BC%80%E6%94%BE%E5%BC%8F%E6%8F%90%E9%97%AE%E6%B3%95
張春興（民102）。現代心理學（重修版）。台北市：東華。
張春興（民102a）。教育心理學-三化取向的理論與實踐（重修二版）。台北市：東華。
陳重光（民101）。應用雲端虛擬化技術結合資訊檢索之演算法教學文章推薦。南台科技大學碩士論文，台南市。
吳靜吉、程炳林（民81）。激勵的學習策略量表之修訂。測驗年刊，39輯，59-78。
劉又瑄（民97）。大學會計系學生人格特質、學習動機、學習風格與學習成效之相關性研究。國立政治大學碩士論文，台北市。
謝鎮宇（民99）。意見探勘在中文評鑑語料之應用。國立交通大學碩士論文，新竹市。
Chang, P.-C., Tseng, H., Jurafsky, D., & Manning, C. D. (2009). Discriminative reordering with Chinese grammatical relations features. Paper presented at the Proceedings of the Third Workshop on Syntax and Structure in Statistical Translation, Boulder, Colorado.
December, J. (1996). Units of Analysis for Internet Communication. Journal of Computer-Mediated Communication, 1(4), 0. doi：10.1111/j.1083-6101.1996.tb00173.x
Gains, J. (1999). Electronic Mail—A New Style of Communication or Just a New Medium?： An Investigation into the Text Features of E-mail. English for Specific Purposes, 18(1), 81-101. doi：http：//dx.doi.org/10.1016/S0889-4906(97)00051-3
Hong, T.-P., Wang, J.-C., & Lin, J.-H. (2007). Semantic Retrieval of Electronic Medical Records Based on Concept Networks. Journal of Internet Technology, 8(4), 423-431.
Huang, W.-C., Lin, M.-C., & Wu, S.-H. (2010). Opinion Sentences Extraction and Polarity Classification Using Automatically Generated Templates. Paper presented at the The 8th NTCIR Workshop, Tokyo, Japan.
Kim, S.-M., & Hovy, E. (2004). Determining the sentiment of opinions. Paper presented at the Proceedings of the 20th international conference on Computational Linguistics, Geneva, Switzerland.
Liu, B. (2012). Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies, 5(1), 1-167.
Luppicini, R. (2007). Review of computer mediated communication research for education. Instructional Science, 35(2), 141-185. doi：10.1007/s11251-006-9001-6
Meng, J., Lin, H., & Yu, Y. (2011). A two-stage feature selection method for text categorization. Computers & Mathematics with Applications, 62(7), 2793-2800. doi：http：//dx.doi.org/10.1016/j.camwa.2011.07.045
Murray, D. E. (2000). Protean Communication： The Language of Computer-Mediated Communication. TESOL Quarterly, 34(3), 397-421. doi：10.2307/3587737
Nguyen, L. V. (2008). Computer mediated communication and foreign language education： Pedagogical features. International Journal of Instructional Technology and Distance Learning, 5(12), 23-44.
O'Reilly, T. (2005). What Is Web 2.0. Retrieved from http：//www.oreilly.com/pub/a/web2/archive/what-is-web-20.html
O'Rourke, B. (2008). The other C in CMC： What alternative data sources can tell us about text-based synchronous computer mediated communication and language learning. Computer Assisted Language Learning, 21(3), 227-251. doi：10.1080/09588220802090253
Payne, J. S., & Whitney, P. J. (2002). Developing L2 Oral Proficiency through Synchronous CMC： Output, Working Memory, and Interlanguage Development. CALICO Journal, 20(1), 7-32.
Payne, S., & Ross, B. (2005). Synchronous CMC, Working Memory, and L2 Oral Proficiency Development. Language Learning &; Technology, 9(3), 35-54.
Pintrich, P. R., & de Groot, E. V. (1990). Motivational and self-regulated learning components of classroom academic performance. Journal of Educational Psychology, 82(1), 33-40. doi：10.1037/0022-0663.82.1.33
Smith, B., Alvarez-Torres, M. a. J., & Zhao, Y. (2003). Features of CMC technologies and their impact on language learners’ online interaction. Computers in Human Behavior, 19(6), 703-729. doi：http：//dx.doi.org/10.1016/S0747-5632(03)00011-6
Stipek, D., Feiler, R., Daniels, D., & Milburn, S. (1995). Effects of Different Instructional Approaches on Young Children's Achievement and Motivation. Child Development, 66(1), 209-223. doi：10.2307/1131201
Walther, J. B. (2007). Selective self-presentation in computer-mediated communication： Hyperpersonal dimensions of technology, language, and cognition. Computers in Human Behavior, 23(5), 2538-2557. doi：http：//dx.doi.org/10.1016/j.chb.2006.05.002
Wang, H.-C., Liu, C.-T., & Huang, T.-H. (2007). A concept-level ontology construction method for automatic summarization. Journal of Internet Technology, 8(4), 381-387.
Yang, C., Lin, K. H. Y., & Chen, H. H. (2007, 2-5 Nov. 2007). Emotion Classification Using Web Blog Corpora. Paper presented at the Web Intelligence, IEEE/WIC/ACM International Conference on, Fremont, CA.