股票市場上每天湧入大量財金新聞，經濟學家Eugene Fama (1970)提出效率市場假說，在半強勢效率市場公開訊息皆已反映在股價上，投資人是否真的無法從這些財金新聞資訊中獲得超額報酬？本研究利用文字探勘從Bloomberg網站獲取大量財金新聞，透過LM (Loughran & McDonald, 2011)、OL (Hu & Liu, 2004)、MPQA (Wilson et al., 2005)三個語意詞庫將財金新聞量化為新聞情緒指數，利用新聞情緒指數建立技術分析模型預測標準普爾500指數走勢，透過向量自回歸VAR統計檢定發現新聞情緒指數與標準普爾500指數無顯著關係；研究發現財金新聞資訊，在其波動強度不夠大時並不會影響標準普爾500指數走勢，波動幅度在未超過2.5個標準差時，股票指數走勢仍依其原有方向移動，即便負面新聞波動幅度超過2.5個標準差時，也不會對標準普爾500指數走勢有明顯影響，然而，我們觀察到當正面新聞波動幅度超過2.5個標準差時，幾天後股票指數走勢開始轉強，有較大幅度的漲幅，而在新聞波動幅度變小回到平均值時，標準普爾500指數走勢開始由強轉弱，開始反轉往趨勢線方向移動。實證結果發現，日常新聞並不會對標準普爾500指數走勢造成影響，但正面新聞數量達到某一程度時能捕捉到股票指數的一段漲幅，LM、OL、MPQA三個不同語意詞庫模型分別漲幅為6.12%、6.02%及4.42%。

The stock market is flooded with a bunch of financial news every day. Economist Eugene Fama (1970) proposed Efficient Market Hypothesis (EMH), stated that stock prices in the Semistrong-form efficient market already fully reflect publicly available information. Is it possible that investors can get exceed returns from the market via daily financial news? To answer this question, our study use text mining to obtain a lot of financial news from the Bloomberg website, we quantify financial news and turn them into financial sentiment index. Then, we utilize financial sentiment index to build the technical analysis model for predicting S&P 500 index trend; we conduct the Vector Autoregression(VAR) statistical test, the result shows that there is no significant relation between financial sentiment index and S&P 500 index. This study finds that the information of financial news does not affect the trend of the S&P 500 index until the intensity fluctuation of the information is strong enough. We mine the textual data from financial news to gain the useful information through LM (Loughran & McDonald, 2011), OL (Hu & Liu, 2004) and MPQA (Wilson et al., 2005) three lexicons, moreover, create the news sentiment index. We consider the news sentiment index as an indicator of stock technical analysis. If the fluctuation range of the news sentiment index does not exceed 2.5 standard deviations, the S&P 500 index continuously will be moving in its original direction. When the volatility of the news sentiment index exceeds 2.5 standard deviations, it will have a significant impact on the S&P 500 index. We employ the discovery to simulate trading strategy in S&P 500 index, and the returns for LM, OL, MPQA three lexicons were 6.12%, 6.02%, 4.42% and, respectively.

Reference
Aase, K.-G. (2011). Text Mining of News Articles for Stock Price Predictions. Master’s thesis of Science in Computer Science, Norwegian University of Science and Technology
Atkins, A., Niranjan, M., & Gerding, E. (2018). Financial news predicts stock market volatility better than close price. The Journal of Finance and Data Science, 4(2), 120-137
Baker, M. & Stein, J. (2004). Market liquidity as a sentiment indicator. Journal of Financial Market, 7(3), 1645-1680.
Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. Journal of Finance, 61(4), 1645-1680.
Bollen, J., & Huina, M. (2011). Twitter mood as a stock market predictor. Computer Society, 44(10), 91-94.
Bollinger, J. (1980). Bollinger Bands. “Bollinger Bands Tutorial.”
https://www.bollingerbands.com/bollinger-band-rules
Brown, G.W., & Cliff, M.T. (2004). Investor sentiment and the near-term stock market. Journal of Empirical Finance, 11(1), 1-27.
Chan, Y., & Wei, K. J. (1996). Political Risk and Stock Price Volatility: The case of Hong Kong. Pacific-Basin Finance Journal, 4(2-3), 259-275
Chan, Y., Chui, A., & Kwok, C. (2001). The impact of salient political and economic news on the trading activity. Pacific-Basin Finance Journal, 9(3), 195-217
Curtin, Richard T, Juster Thomas, Morgan James N. (1998). Survey Estimates of Wealth: An Assessment of Quality. National Bureau of Economic Research, 473 - 552
Fama, E., 1970. Efficient capital markets: A review of theory and empirical work. The Journal of Finance, Volume 25, 383–417.
Fang, L., & Peress, J. (2009). Media coverage and the cross-section of stock returns. Journal of Finance, 64(5), 2023-2052.
Financial Sentiment Dictionary(LM): Loughran and McDonald (2011)
https://sraf.nd.edu/textual-analysis/resources/#LM%20Sentiment%20Word%20Lists
Fung, G. P. C., Yu, J. X., & Lam, W. (2003). Stock Prediction: Integrating Text Mining Approach Using Real-time News. The 7th IEEE International Conference on Computational Intelligence for Financial Engineering (CIFE), 395-402.
Gidofalvi, G. (2001). Using News Articles to Predict Stock Price Movements. University of California, San Diego: Department of Computer Science and Engineering.
Gu, Q., Cai, Z., Zhu, L., & Huang, B. (2008). Data Mining on Imbalanced Data Sets. In International Conference on Advanced Computer Theory and Engineering. Phuket, Thailand. IEEE. 1020-1024.
Huang, R.-J. (2018). On the Use of Mining News Reports to Predict S&P 500 Trends. Master’s thesis. Department of Accountancy National Cheng Kung University
Hu, M., & Liu, B. (2004). Mining and summarizing customer reviews. 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2004), pages 168-177.
Leung,Joseph Man-joe & Chong, Terence Tai-leung (2002). An empirical comparison of moving average envelopes and Bollinger Bands. Applied Economics Letters, 10(6), 339-341
Kalyani, J., Bharathi, P., & Jyothi, P. (2016). Stock Trend Prediction Using News Sentiment Analysis. International Journal of Computer Science & Information Technology (IJCSIT), 8(3), 67-76.
Konchady, M. (2006). Text Mining Application Programming. Boston, MA: Charles River Media
Lento, C., Gradojevic, N., & Wright, C. S. (2007). Investment information content in Bollinger Bands? Applied Financial Economics Letters, 3(4), 263-267
Loughran, T., & McDonald, B. (2011). When is a liability not a liability? textual analysis, dictionaries, and 10-ks. The Journal of Finance, 66(1), 35-65.
Marko Kolanovic & Rajesh T. Krishnamachari. (2017), Big Data and AI Strategies Machine Learning and Alternative Data Approach to Investing, Published in JPMorgan.
Meyers, T. (2011). The Technical Analysis Course Learn How to Forecast and Time the Market (5th Ed). McGrawHill
Moat, H. et al. (2013). Quantifying Wikipedia Usage Patterns Before Stock Market Moves. Scientific Reports. 3, 1801, 1-5
Nechio, Fernanda & Regan, Rebecca (2016). Fed Communication: Words and Numbers. FRBSF Economic Letter. 2016-26
Opinion Lexicon(OL): Hu and Liu (2004)
https://en.wikipedia.org/wiki/Natural_language_processing
Prattle.co. https://prattle.co/fed-index-and-equities/
Preis, T., Moat, H. & Stanley, H. (2013). Quantifying Trading Behavior in Financial Markets Using Google Trends. Scientific Reports, 3, 1684.
Schumaker, R. P., & Chen, H. (2009). Textual Analysis of Stock Market Prediction Using Breaking Financial News: The AZFin Text System. ACM Transactions on Information Systems (TOIS), 27(2), 12.
Soni, A., van Eck, N. J., & Kaymak, U. (2007, April). Prediction of stock price movements based on concept map information. In 2007 IEEE Symposium on Computational Intelligence in Multi-Criteria Decision-Making (pp. 205-211).
Stanford CoreNLP Tutorials, https://stanfordnlp.github.io/CoreNLP/tutorials.html
Tetlock, P. C., Saar-Tsechansky, M. & Macskassy, S. (2008). More than words: Quantifying language to measure firms’ fundamentals. The Journal of Finance, 63, 1437-1467.
Vu, T., Chang, S., Ha, Q., & Collier, N. (2012). An experiment in integrating sentiment features for tech stock prediction in twitter. Mumbai, India, The COLING 2012 Organizing Committee, pp. 23-38.
Wei, Y.-C., Lu, Y.-C., & Hsu, Y.-J. (2018). News and Investor Sentiments: The impact on trading behavior. European Financial Management Association 2018 Annual Meetings. Università Cattolica del Sacro Cuore, Milan
Werner, A., & Murray, Z. F. (2004). Is all that talk just noise? The information content of internet stock message boards. Journal of Finance, 59(3), 1259-1294.
Wilson, T., Wiebe, J., & Hoffmann, P. (2005). Recognizing contextual polarity in phrase level sentiment analysis. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing.
Wilson et al. (2005). Multi-Perspective Question Answering Subjective Lexicon (MPQA): http://mpqa.cs.pitt.edu/corpora/gfbf/
Wüthrich, B., Permunetilleke, D., Leung, S., Lam, W., Cho, V., & Zhang, J. (1998). Daily prediction of major stock indices from textual www data. Hkie transactions, 5(3), 151-156.
Yahoo! Finance website: https://finance.yahoo.com/quote/%5EGSPC/history?p=%5EGSPC
Yu, Y., Duan, W., & Cao, Q. (2013). The impact of social and conventional media on firm equity value: A sentiment analysis approach. Decision Support Systems, 55(4), 919-926.
Zhang, J. L., Härdle, W. K., Chen, C. Y., & Bommes, E. (2016). Distillation of News Flow into Analysis of Stock Reactions. Journal of Business & Economic Statistics, 34(4), 547-563.
Zhou, Z. H. (2003). Three Perspectives of Data Mining. Journal of Artificial Intelligence, 143(1), 139-149