國內外實證研究文獻證實，情緒特徵為報酬的重要因子，如何捕捉情緒相關變數預測報酬，成為百家爭鳴的課題。然而傳統輿情分析的方式大都侷限於數字型態結構化資料，而伴隨社群媒體普及，文字、聲音、影像的非結構化資料也成為我們的分析對象之一，如何從非結構化的文字中，萃取出有用的重要資訊或知識逐漸成為主流。本研究首度探討新聞輿情之時間框架與新聞輿情的驅動力來源，首先藉由謝委霖（2015）的財金情緒辭庫計算新聞情緒字眼比例，接著聚焦於不同頻率下，以計量方法了解新聞輿情與市場之互動關係以及好壞消息對於股價衝擊的反應時間，並進一步理解其釋股價偏離基本價值的原因，最後利用自然語言處理技術-Word2Vec，以不同維度表達字詞的意義，提升情感分析的廣度與深度。結果顯示: (一)新聞輿情在週頻下對於資產定價較具影響力(二)新聞輿情影響力來自於散戶交易行為(三)好消息反應快速且持續，壞消息則反應落後(四)Word2vec字詞向量化技術確實能增加預測股價趨勢之準確率

Past studies have confirmed that sentiment is one of the important factors affecting market returns. How to capture the sentiment indicator is the main subject. Traditional methods mostly involve analyzing structural data. With the popularization of social media, unstructured data such as words, sounds and videos have become significant. How to extract useful information from texts gradually become mainstream. For the first time, this study explored the time frame of news sentiment and the driving force of news polarity. First of all, financial sentiment database in Hsieh (2015) was used to calculate the proportion of emotion words in news and then focused on different frequencies to use quantitative methods to understand the interaction relationship between news sentiment and market. Furthermore, we found the reaction time of the stock price shock which good or bad news made and further understood the reason why the stock price deviated from the basic value. Finally, we used natural language processing technology-Word2Vec to express the meaning of words in different dimensions to enhance the sentiment analysis breadth and depth. The results show that: (1) News sentiment is more influential to asset pricing at weekly frequency (2) The influence of news sentiment comes from trading behavior of individual investors (3) Good news responds rapidly and continuously while bad news travels slowly (4) Word2vec technology can increase accuracy of predicting stock price trends

論文審定書 i
摘要 ii
ABSTRACT iii
LIST OF FIGURES vi
LIST OF TABLES vii
Chapter 1 INTRODUCTION 1
1.1 Background Information 1
1.2 Research Purpose 3
1.3 Research Contribution 5
Chapter 2 LITERATURE REVIEW 6
2.1 Sentiment Measurement, Investor Sentiment Related Literature 6
2.2 Text Mining Related Literature 9
Chapter 3 METHODOLOGY 13
3.1 Data Description 13
3.2 Definition of News Polarity Variables 14
3.3 The Interaction Between News Sentiment and Return 15
3.3.1. Driving Forces of News Sentiment Prediction 18
3.3.2. News Information Affect The Stock Price Time Frame 20
3.4 Word Vectorization Analysis 22
3.5 Whether News Information has Predictive Ability 24
Chapter 4 EMPIRICAL RESULTS 24
4.1 Descriptive Statistics 24
4.1.1 News Sentiment Descriptive statistics 25
4.1.2 News Sentiment and Market Data 27
4.2 Word Vectorization 30
4.3 The Relationship between Market and News Sentiment 31
4.4 Driving Forces of News Sentiment 34
4.5 News Information Affect The Stock Price Time Frame 36
4.6 Whether News Information has Predictive Ability 38
Chapter 5 CONCLUSION 40
REFERENCE 43
APPENDIX 47

英文部分
Akita, R., Yoshihara, A., Matsubara, T., Uehara, K., (2016). Deep learning for stock prediction using numerical and textual information. IEEE/ACIS 15th International Conference on Computer and Information Science (ICIS). doi: 10.1109/ICIS.2016.7550882
BAKER, M., & WURGLER, J. (2006). Investor Sentiment and the Cross-Section of Stock Returns. The Journal Of Finance, 61(4), 1645-1680. doi: 10.1111/j.1540-6261.2006.00885.x
Barone-Adesi, G., Mancini, L., & Shefrin, H. (2012). Sentiment, Asset Prices, and Systemic Risk. SSRN Electronic Journal. doi: 10.2139/ssrn.1953621
Ben-Rephael, A., Kandel, S., & Wohl, A. (2012). Measuring investor sentiment with mutual fund flows. Journal Of Financial Economics, 104(2), 363-382. doi: 10.1016/j.jfineco.2010.08.018
Bollen, J., Mao, H., & Zeng, X. (2011). Twitter mood predicts the stock market. Journal Of Computational Science, 2(1), 1-8. doi: 10.1016/j.jocs.2010.12.007
Bijalwan, V., Kumar, V., Kumari, P., & Pascual, J. (2014). KNN based Machine Learning Approach for Text and Document Mining. International Journal Of Database Theory And Application, 7(1), 61-70. doi: 10.14257/ijdta.2014.7.1.06
Baker, M., & Stein, J. (2004). Market liquidity as a sentiment indicator. Journal Of Financial Markets, 7(3), 271-299. doi: 10.1016/j.finmar.2003.11.005
Chi, L., Zhuang, X., & Song, D. (2012). Investor sentiment in the Chinese stock market: an empirical analysis. Applied Economics Letters, 19(4), 345-348. doi: 10.1080/13504851.2011.577003
Curme, C., Preis, T., Stanley, H., & Moat, H. (2014). Quantifying the semantics of search behavior before stock market moves. Proceedings Of The National Academy Of Sciences, 111(32), 11600-11605. doi: 10.1073/pnas.1324054111
Duhigg, C. (2006). A Smarter Computer to Pick Stocks.New York Times :www.nytimes.com/2006/11/24/business/24trading.html.

Dougal, C., Engelberg, J., Garcia, D., & Parsons, C. (2011). Journalists and the Stock Market. SSRN Electronic Journal. doi: 10.2139/ssrn.1784431
Ertugrul, M., Lei, J., Qiu, J., & Wan, C. (2017). Annual Report Readability, Tone Ambiguity, and the Cost of Borrowing. Journal Of Financial And Quantitative Analysis, 52(02), 811-836. doi: 10.1017/s0022109017000187
Fama, E. (1970). Efficient Capital Markets: A Review of Theory and Empirical Work. The Journal Of Finance, 25(2), 383. doi: 10.2307/2325486
Edelen, R., Marcus, A., & Tehranian, H. (2010). Relative Sentiment and Stock Returns. Financial Analysts Journal, 66(4), 20-32. doi: 10.2469/faj.v66.n4.2
Fama, E., & French, K. (1993). Common risk factors in the returns on stocks and bonds. Journal Of Financial Economics, 33(1), 3-56. doi: 10.1016/0304-405x(93)90023-5
FANG, L., & PERESS, J. (2009). Media Coverage and the Cross-section of Stock Returns. The Journal Of Finance, 64(5), 2023-2052. doi: 10.1111/j.1540-6261.2009.01493.x
Gervais, S., & Odean, T. (1997). Learning To Be Overconfident. SSRN Electronic Journal. doi: 10.2139/ssrn.36313
Hong, H., Lim, T., & Stein, J. (2000). Bad News Travels Slowly: Size, Analyst Coverage, and the Profitability of Momentum Strategies. The Journal Of Finance, 55(1), 265-295. doi: 10.1111/0022-1082.00206
Heston, S., & Sinha, N. (2017). News vs. Sentiment: Predicting Stock Returns from News Stories. Financial Analysts Journal, 73(3), 67-83. doi: 10.2469/faj.v73.n3.3
Heston, S., & Sinha, N. (2017). News vs. Sentiment: Predicting Stock Returns from News Stories. Financial Analysts Journal, 73(3), 67-83. doi: 10.2469/faj.v73.n3.3
Huang, D., Jiang, F., Tu, J., & Zhou, G. (2014). Investor Sentiment Aligned: A Powerful Predictor of Stock Returns. Review Of Financial Studies, 28(3), 791-837. doi: 10.1093/rfs/hhu080
Jegadeesh, N., & Titman, S. (1993). Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency. The Journal Of Finance, 48(1), 65. doi: 10.2307/2328882
Joseph, K., Babajide Wintoki, M., & Zhang, Z. (2011). Forecasting abnormal stock returns and trading volume using investor sentiment: Evidence from online search. International Journal Of Forecasting, 27(4), 1116-1127. doi: 10.1016/j.ijforecast.2010.11.001
Khadjeh Nassirtoussi, A., Aghabozorgi, S., Ying Wah, T., & Ngo, D. (2014). Text mining for market prediction: A systematic review. Expert Systems With Applications, 41(16), 7653-7670. doi: 10.1016/j.eswa.2014.06.009
Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica, 47(2), 263. doi: 10.2307/1914185
Liew, J., & Wang, G. (2015). Twitter Sentiment and IPO Performance: A Cross-Sectional Examination. SSRN Electronic Journal. doi: 10.2139/ssrn.2567295
Liao, T., Huang, C., & Wu, C. (2011). Do fund managers herd to counter investor sentiment?. Journal Of Business Research, 64(2), 207-212. doi: 10.1016/j.jbusres.2010.01.007
Manela, A., & Moreira, A. (2017). News implied volatility and disaster concerns. Journal Of Financial Economics, 123(1), 137-162. doi: 10.1016/j.jfineco.2016.01.032
Nikkinen, J., & Vähämaa, S. (2010). Terrorism and Stock Market Sentiment. Financial Review, 45(2), 263-275. doi: 10.1111/j.1540-6288.2010.00246.x
Patel, J., Shah, S., Thakkar, P., & Kotecha, K. (2015). Predicting stock and stock price index movement using Trend Deterministic Data Preparation and machine learning techniques. Expert Systems With Applications, 42(1), 259-268. doi: 10.1016/j.eswa.2014.07.040
Rakowski, D., Shirley, S., & Stark, J. (2017). Is All That Twitters Gold? Social Media Attention and Stock Returns. SSRN Electronic Journal. doi: 10.2139/ssrn.3010915
Ro, S. (2012). Art Cashin: We May Have Just Witnessed the Presence of Artificial Intelligence in the Stock Market. Business Insider: www.businessinsider.com/art-cashin-artificial-intelligence-stock-market-2012-3
Shirata, C., & Sakagami, M. (2008). An Analysis of the “Going Concern Assumption”: Text Mining from Japanese Financial Reports. Journal Of Emerging Technologies In Accounting, 5(1), 1-16. doi: 10.2308/jeta.2008.5.1.1
Sinha,S. (2016): « How is big data analytics used for stock market trading (quant and Non-quant trading)? », Quora. Retrieved April 05, 2018, from https://www.quora.com/How-is-big-data-analytics-used-for-stock-market-trading-quant-and-Non-quant-trading
Shirata, C., Takeuchi, H., Ogino, S., & Watanabe, H. (2011). Extracting Key Phrases as Predictors of Corporate Bankruptcy: Empirical Analysis of Annual Reports by Text Mining. Journal Of Emerging Technologies In Accounting, 8(1), 31-44. doi: 10.2308/jeta-10182
Shiller, R., Fischer, S., & Friedman, B. (1984). Stock Prices and Social Dynamics. Brookings Papers On Economic Activity, 1984(2), 457. doi: 10.2307/2534436
Zouaoui, M., Nouyrigat, G., & Beer, F. (2011). How Does Investor Sentiment Affect Stock Market Crises? Evidence from Panel Data. Financial Review, 46(4), 723-747. doi: 10.1111/j.1540-6288.2011.00318.x

中文部分
周賓凰、張宇志、林美珍(2007)，「投資人情緒與股票報酬互動關係」，證券市場發展季刊，19:2，153-190。
鍾任明、李維平、吳澤民(2007)，「運用文字探勘於日內股價漲跌趨勢之研究」，中華管理評論國際學報，2007 年 2 月第十卷一期
謝委霖 (2015)，「從財金新聞預測公司財報之營收走勢」，國立中山大學資訊管理學系研究所碩士論文。