文字探勘為近年來快速發展且逐漸被重視之技術，能夠將非結構化資料轉化為結構化資料以利使用者進行後續分析，相關財經研究領域之應用如探討公司財務報表、新聞專欄、社群媒體輿論等文字資訊。而本研究希望能藉由蒐集網路財經新聞與文字探勘資料整理的技術，將新聞中的情緒字詞量化成新聞情緒分數，並透過新聞情緒分群、時間序列迴歸模型、交易策略建構等研究方式，探討新聞情緒與股價報酬的關係。
實證結果顯示，當期新聞情緒能夠與當期股價報酬呈現相同走勢，而對應下期股價報酬，正面新聞情緒已無法帶來正向報酬，表示股價對正面情緒之新聞反應快速且存在投資人過度樂觀的現象，對於負面情緒的新聞則反應落後，仍然呈現負累積報酬的走勢。另外，新聞情緒風險因子在大規模公司投資組合中大部分較不顯著，其中在因子顯著的負面新聞情緒分類中，發現負面新聞對小規模公司的股價衝擊會比對大規模公司來的嚴重。藉由上述觀察，本研究將新聞情緒作為交易策略的賣出訊號，搭配簡單的進場條件建構交易策略，在不考慮交易成本的情況下，以新聞情緒做為賣出訊號的策略績效表現優於未以新聞情緒做為賣出訊號的策略績效表現，說明新聞情緒應用於交易策略的有效性。

Text mining has developed rapidly in recent years. It can convert unstructured data into structured data for users to perform subsequent analysis. Applications in related financial research fields such as discussing company financial statements, news reports, and social media opinion and other text information. This study hopes to quantify the emotional words in the news into news sentiment scores through collecting online financial news, and by using research methods such as news sentiment clustering, time series regression models, and trading strategy construction to explore the relationship between news sentiment and stock returns.
The empirical results show that (1) the current news sentiment can show the same trend as the current stock returns, and positive news can no longer bring positive rewards in the next period, but the news of negative emotions still shows a trend of negative cumulative returns. (2) News sentiment risk factors are mostly insignificant in large-scale company portfolios. Among the negative news sentiment categories, it is found that the impact of negative news on stock prices of small-scale companies will be more severe than on large-scale companies. (3) Construct trading strategy with a simple entry conditions and use news sentiment as a sell signal for trading strategy, this trading strategy’s performance is better than the performance of the trading strategy without using news sentiment as a sell signal. It explains the value of news sentiment applied in trading strategies.

論文審定書 i
摘要 ii
Abstract iii
目 錄 iv
圖 次 vi
表 次 vii
第一章 緒論 1
第一節 研究動機 1
第二節 研究目的 2
第三節 研究架構 3
第二章 文獻回顧 4
第一節 影響投資人情緒的因素 4
第二節 投資人情緒與股票市場分析 5
第三節 新聞情緒 8
第三章 研究方法與模型建立 10
第一節 研究期間與資料來源 10
第二節 研究流程 10
第三節 文本資料處理 11
第四節 新聞情緒計算 13
第五節 新聞情緒分群與累積報酬率 14
第六節 多因子模型 15
第七節 交易策略介紹 17
第四章 實證結果 19
第一節 敘述統計 19
第二節 新聞情緒與股價報酬的關係 25
第三節 時間序列迴歸模型分析結果 32
第四節 交易策略績效表現 45
第五章 結論與建議 52
第一節 結論 52
第二節 研究建議 53
參考文獻 54
附錄 57

一、 中文部分
1. 余宛真(2015)，投資人情緒、公司治理與股票報酬之研究，國立高雄應用科技大學金融系金融資訊碩士班碩士論文。
2. 李顯儀、吳幸姬、李亮君(2008)，投資人對股票報酬與風險的關心程度之探討，台灣管理學刊，8(2)，71-94。
3. 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，第十九卷第二期，153-190。
4. 林宜萱(2013)，財經領域情緒辭典之建置與其有效性之驗證-以財經新聞為元件，國立臺灣大學會計學研究所論文。
5. 陳建宏(2018)，「新聞輿情、報酬與投資人交易行為，國立中山大學財務管理學系研究所論文。
6. 廖國翔(2002)，注意力、情緒對投資決策之影響，國立政治大學財務管理研究所碩士論文。
7. 蔡佩蓉、王元章、張眾卓(2009)，投資人情緒、公司特徵與台灣股票報酬之研究，經濟研究，第四十五卷第二期，頁273-322。
8. 鄭高輯、林泉源(2010)，投資人情緒對投機型股票報酬之影響，商略學報 ，第2卷，第1期，頁21 - 35。
9. 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研究所論文。

二、 英文部分
1. Baker M., and Wurgler J. (2000). The Equity Share in New Issues and Aggregate Stock Returns. Journal of Finance, 55, 2219-2257.
2. Baker M., and Wurgler J. (2006). Investor Sentiment and the Cross-section of Stock Returns. Journal of Finance, 61, 1645-1680.
3. Banz R. W. (1981). The relationship between return and market value of common stocks. Journal of Financial Economics, 9, 3-18.
4. Barber B. M., and Odean T. (2001). Boys will be Boys: Gender, Overconfidence and Common Stock Investment. Quarterly Journal of Economics, 116, 261-292.
5. Barber B. M., and Odean T. (2008). All That Glitters: The Effect of Attention and News on the Buying Behavior of Individual and Institutional Investors. Review of Financial Studies, 21(2), 785-818.
6. Barber B. M., Odean T., and Zhu N. (2006). Do Noise Traders Move Markets? Working Paper, Department of Finance, University of California at Davis.
7. Bergman N. K., and Roychowdhury S. (2008). Investor sentiment and corporate disclosure. Journal of Accounting Research, 46(5), 1057-1083.
8. Brown G. W., and Cliff M. T. (2004). Investor sentiment and the near-term stock market. Journal of Empirical Finance, 11(1), 1-27.
9. Brown G. W., and Cliff M. T. (2005). Investor Sentiment and Asset Valuation. The Journal of Business, 78(2), 405-440.
10. Bulkley G., and Herrerias R. (2005). Does the Precision of News Affect Market Underreaction? Evidence from Returns Following Two Classes of Profit Warnings. European Financial Management, vol. 11, No. 5, 603-624.
11. Carhart M. M. (1997). On persistence in mutual fund performance. Journal of Finance, 52(1), 57-82.
Chang S.C., Chen S. S., Chou R. K., and Lin Y. H. (2008). Weather and intraday patterns in stock returns and trading activity. Journal of Banking & Finance, vol.32, 2008, 1754 – 1766.
12. Clarke R. G., and Statman M. (1998). Bullish or Bearish? Financial Analysts Journal, 54(3), 63-72.
13. Cooper M. J., Gulen H. and Schill M. J. (2008). Asset growth and the cross-section of stock returns. Journal of Finance, 63(4), 1609-1651.
14. De Bondt W. P. M. (1993). Betting on trends: Intuitive forecasts of financial risk and return. International Journal of Forecasting, vol. 9, issue 3, 355-371.
15. Engelberg J. E., and Parsons C. A. (2011). The Causal Impact of Media in Financial Markets. The Journal of Finance, 66(1), 67–97.
16. Fama E. F., and French K. R. (1993). Common Risk Factors in the Returns on Stocks and Bonds. Journal of Financial Economics, vol. 33(1), 3-56.
17. Fama E. F., and French K. R. (2015). A five-factor asset pricing model. Journal of Financial Economics, 116(1), 1-22.
18. Gemmill G., and Thomas D. C. (2002). Noise Trading, Costly Arbitrage, and Asset Prices: Evidence from Closed‐end Funds. The Journal of Finance, vol. 57, issue 6, 2571-2594.
19. Gemmill G., and Thomas D. C. (2013). Are IPO Investors Rational? Evidence from Closed-End Funds. European Journal of Finance, 23(14), 1-24.
20. Gregory W. B., and Cliff M. T. (2004). Investor Sentiment and the Near Term Stock Market. Journal of Empirical Finance, 11(1), 1-27.
21. Hirshleifer D. A., and Shumway T. (2003), Good day sunshine: Stock returns and the weather, The Journal of Finance 58, 1009-1032.
22. Howarth E., and Hoffman M. S. (1984). A multidimensional approach to the relationship between mood and weather. British Journal of Psychology, vol. 75, issue 1.
23. Kamstra M. J., Kramer L. A., and Levi M. D. (2000). Losing Sleep at the Market: The Daylight-Savings Anomaly. The American Economic Review, 90(4), 1005-1011.
24. Kamstra, M. J., Kramer, L. A., & Levi, M. D. (2003). Winter blues: A SAD stock market cycle. The American Economic Review, 93(1), 324-343.
25. Keim D. B., and Madhavan A., (1995). Anatomy of the Trading Process Empirical Evidence on the Behavior of Institutional Traders. Journal of Financial Economics, vol. 37, issue 3, 371-398.
26. Krivelyova A., and Robotti C. (2003). Playing the Field: Geomagnetic Storms and the Stock Market. Federal Reserve Bank of Atlanta, Working Paper, No. 2003-2005b.
27. Lee C.M.C., and Swaminathan B. (2000). Price Momentum and Trading Volume. Journal of Finance, 55(5), 2017-2069.
28. Leinweber D., and Sisk J. (2011). Event-Driven Trading and the “New News.” The Journal of Portfolio Management, 38(1), 110–124.
29. Nofsinger J. (2001). The impact of public information on investors, Journal of Banking & Finance, 25, 1339-1366.
Rosenberg B., Reid K., and Lanstein R. (1985). Persuasive evidence of market inefficiency. The Journal of Portfolio Management, 11(3), 9-16.
30. Sankaraguruswamy S., Shen J., and Yamada T. (2006), Impact of firm-specific public information on the relation between prices and trading, Working Paper, National University of Singapore.
31. Schmeling Maik (2006). Institutional and individual sentiment: smart money and noise trader risk? International Journal of Forecasting, 23 (1), 127-145.
32. Song Q., Yang S. Y., and Liu A. (2017). Stock portfolio selection using learning-to-rank algorithms with news sentiment. Neurocomputing, vol. 264, 20-28.
33. Tetlock P. C. (2010). Does Public Financial News Resolve Asymmetric Information? The Review of Financial Studies, vol. 23, issue 9, 3520–3557.
34. Yang, Chunpeng, and Liyun Zhou (2015). Investor trading behavior, investor sentiment and asset prices. The North American Journal of Economics and Finance, 34, 42-62.