臺灣博碩士論文加值系統

在現今這個大數據時代，分析海量資料是一門重要的研究。其中利用自然
語言處理（Natural Language Processing）之技術分析大量文字，從中解析並取得有價值的資訊，是一項熱門議題。透過自然語言處理技術，可以採
用自動化的方式讓電腦分析人類的語言架構，進而了解文句之間的含意；
其優勢為以更快的速度處理以往需要花費許多人力統計的巨量資料。經已
知研究發現，透過語意情緒詞彙分析，可以更有效的解讀人們對特定議題
的情感關係。然而在不同領域範圍的情緒詞彙，通常會有著不同的含意。
在目前已知的情緒字典中，較少針對特定領域建構情緒字典，而以中文為
背景的情緒字典更是稀少。因此，本研究希望能擴增以中文為主的財務情
緒字典，用以做為未來財務文本研究與實驗的基石。本研究將以Loughran
和McDonald於2008年所提供的英文情緒字典為基底進行翻譯，以多部中
英財務字典進行交叉比對，並使用一段時間內的雅虎中文財務新聞進行詞
彙驗證，建置一部中文財務情緒字典。在實驗與研究中，會以此中文財務
情緒字典做為解決分類問題的特徵值之一，以驗證此中文財務情緒字典在
文字分析中之有效性。

Natural language processing (NLP) is an important research field, in which sentiment analysis is one of the popular research topics. Sentiment lexicon is a one of the vital resources in sentiment analysis. However, there are usually different meanings for a word in different fields of context. Therefore, a domain-specific lexicon, such as financial-specific sentiment lexicon becomes neccessary for different fields of sentiment analysis. But, for now, most of the financial sentiment lexicons are in English. As a result, the purposed of the thesis is to build a Chinese financial sentiment lexicon and apply it on the sentiment
analysis for Chinese finance news. We first translate the English financial sentiment lexicon propose by Loughran and McDonald (2008) to Chinese via the 3 different English-Chinese financial lexicons and Google translate. We then use
a large amount of Chinese financial news to validate the resulting lexicons. After that, we use the resulting Chinese financial sentiment lexicon to predict the polarity of Chinese financial news. The results show that using Chinese financial sentiment lexicons could enhance the accaracy for the sentiment polarity prediction problem.

1 緒論. . . . . . . . . . . . . . . . . . . . . . . . . .1
2 文獻探討. . . . . . . . . . . . . . . . . . . . .. . . . .4
2.1 自然語言處理. . . . . . . . . . . . . . . . . . . .. . 4
2.2 情緒詞彙分析. . . . . . . . . . . . . . . . . . .. . . 5
2.3 財務情緒字典. . . . . . . . . . .. . . . . . . . . . . 7
2.4 文字分析於財務上之應用. . . . . . . . . . . . . . . . . 7
2.5 中文財務情緒詞彙字典. . . . . . . . . . . . . . . . . . 9
2.6 支持向量機. . . . . . . . . . . . . . . . . . . . . . . 9
3 建立中文財務情緒字典. . . . . . . . . . . . . . . . . .. .11
3.1 英文財務情緒字典. . . . . . . . . . . . . . . . . . . . 12
3.2 使用多重英漢字典翻譯英文財務情緒字典. . . . . . . . . . . 12
3.3 驗證翻譯後之中文財務情緒字典. . . . . . . . . . . . . . 14
3.3.1 用以驗證字典之財務新聞. . . . . . . . . . . . ... . . 14
3.3.2 財務新聞之文字前處理. . . . . . . . . . . . .. . . . 16
3.3.3 驗證中文財務情緒字典. . . . . . . . . . . . . ... . . 18
3.4 與文獻中其他中文財務情緒字典之比較. . . . . . . . . . . . 23
4 中文財務情緒字典於新聞情緒之應用. . . . . . . . . . . .. .26
4.1 中文財務新聞. . . . . . . . . . . . . . . . . . . . . 26
4.2 中文財務新聞之情緒性標簽. . . . . . . . . .. . . . . . . 27
4.2.1 Kappa一致性係數. . . . . . . . . . . . . . . . . . . 29
4.3 中文財務新聞資料前處理. . . . . . . . . . . . . . . . 30
4.4 實驗相關設定. . . . . . . . . . . . . . . . . . . . . 31
4.5 實驗結果及分析. . . . . . . . . . . . . . . . . . . . 32
5 結論. . . . . . . . . . . . . . . . . . . . . . . . . .37
Bibliography . . . . . . . .. . . . . . . . . . . . . . . 38

[1] D. Bamman and N. A. Smith. Learning Latent Personas of Film Characters. In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, pages 352–361, 2013.
[2] S. Bird, E. Klein, and E. Loper. Natural Language Processing with Python. O’Reilly Media, Inc., 2009.
[3] D. M. Blei, A. Y. Ng, and M. I. Jordan. Latent Dirichlet Allocation. Journal of Machine Learning Research, 3:993–1022, 2003.
[4] J. Bollen, H. Mao, and X. Zeng. Twitter Mood Predicts the Stock Market. Journal of Computational Science, 2(1):1–8, 2011.
[5] G. W. Brown and M. T. Cliff. Investor Sentiment and the Near-Term Stock Market. Journal of Empirical Finance, 11(1):1–27, 2004.
[6] K. W. Church and P. Hanks. Word Association Norms, Mutual Information, and Lexicography. Computational Linguistics, 16(1):22–29, 1990.
[7] D. Ferrucci, E. Brown, J. Chu-Carroll, J. Fan, D. Gondek, A. A. Kalyanpur, A. Lally, J. W. Murdock, E. Nyberg, J. Prager, et al. Building Watson: An
Overview of the DeepQA Project. AI magazine, 31(3):59–79, 2010.
[8] B. Fu, J. Lin, L. Li, C. Faloutsos, J. Hong, and N. Sadeh. Why People Hate Your App: Making Sense of User Feedback in a Mobile App Store. In Proceedings
of the 19th ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining, pages 1276–1284, 2013.
[9] D. Gr¨abner, M. Zanker, G. Fliedl, and M. Fuchs. Classification of Customer Reviews Based on Sentiment Analysis. Springer, 2012.
[10] B. F. Green Jr, A. K. Wolf, C. Chomsky, and K. Laughery. Baseball: An Automatic Question-Answerer. In Proceedings of the 19th Western Joint Computer Conference, pages 219–224, 1961.
[11] M. Joshi, D. Das, K. Gimpel, and N. A. Smith. Movie Reviews and Revenues:An Experiment in Text Regression. In Proceedings of Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages 293–296,2010.
[12] S. Kogan, D. Levin, B. R. Routledge, J. S. Sagi, and N. A. Smith. Predicting Risk From Financial Reports with Regression. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, pages
272–280, 2009.
[13] L. Lamel, J.-L. Gauvain, and G. Adda. Lightly Supervised and Unsupervised Acoustic Model Training. Computer Speech & Language, 16(1):115–129, 2002.
[14] T. Loughran and B. McDonald. When is a Liability Not a Liability? Textual Analysis, Dictionaries, and 10-Ks. The Journal of Finance, 66(1):35–65,2011.
[15] J. B. Lovins. Development of a Stemming Algorithm. MIT Information Processing Group, Electronic Systems Laboratory, 1968.
[16] A. Mahajan, L. Dey, and S. M. Haque. Mining Financial News for Major Events and Their Impacts on the Market. In Proceedings of IEEE/WIC/ACM on Web Intelligence and Intelligent Agent Technology, volume 1, pages 423–426, 2008.
[17] B. O’Connor, R. Balasubramanyan, B. R. Routledge, and N. A. Smith. From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series. In Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media , pages 122–129, 2010.
[18] B. Pang, L. Lee, and S. Vaithyanathan. Thumbs Up?: Sentiment Classification Using Machine Learning Techniques. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, pages 79–86, 2002.
[19] R. P. Schumaker and H. Chen. Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFin Text System. In Proceedings of the 12th Americas Conference on Information Systems , 27(2):1–29, 2009.
[20] M.-F. Tsai and C.-J. Wang. Risk Ranking From Financial Reports. In Advances in Information Retrieval, pages 804–807. 2013.
[21] P. D. Turney. Thumbs Up or Thumbs Down?: Semantic Orientation Applied to Unsupervised Classification of Reviews. In Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, pages 417–424,
2002.
[22] C.-J. Wang, M.-F. Tsai, T. Liu, and C.-T. Chang. Financial Sentiment Analysis for Risk Prediction. In Proceedings of the 6th International Joint Conference
on Natural Language Processing, pages 802–808, 2013.
[23] W. J. Wilbur and K. Sirotkin. The Automatic Identification of Stop Words.
Journal of Information Science, 18(1):45–55, 1992.
[24] Y. Xia, L. Wang, K.-F. Wong, and M. Xu. Lyric-Based Song Sentiment Classification with Sentiment Vector Space Model. In Proceedings of the 46th Annual Meeting of the Association of Computational Linguistics, pages
133–136, 2008.
[25] 林宜萱. Creating and Verifying Sentiment Dictionary of Finance and Economics via Financial News. National Taiwan University, 2013.
[26] Cortes, Corinna and Vapnik, Vladimir Support-Vector Networks. Machine Learning, 20(3):273–297, 1995.
[27] 蔡爾逸. Predicting Price of Real Estate in Urban Area Using Support Vector Machine. National Central University, 2012.
[28] Cronbach, Lee J Coefficient Alpha and the Internal Structure of Tests. Psychometrika, 16(3): 297–334, 1951.
[29] G. F. Kuder, and M. W. Richardson The Theory of the Estimation of Test Reliability. Psychometrika, 2(3): 151–160, 197.
[30] K.R Murphy, and O.D. Charles. Psychological Testing.” Principles, and Applications. Englewood Cliffs, 1988.
[31] Smeeton, Nigel C. Early History of the Kappa Statistic. JSTOR, 1985.
[32] Geertzen, J. Inter-Rater Agreement with Multiple Raters and Variables. Retrieved October 27, 2015, from https://nlp-ml.io/jg/software/ira/. 2012.