本研究擬建構個股投資人情緒指標，將其區分出理性情緒與非理性情緒，並以機器學習或深度學習來預測個股極端漲跌情形，再觀察台灣市場投資人情緒對於極端漲與極端跌情形的不對稱性。本研究將投資人情緒定義為：投資人基於某種信息，對資產價格有預期，並依此採取相對的交易。而情緒又可區分為理性情緒與非理性情緒，理性情緒為投資人對資訊的不偏反應，會使股價正確的反應其內含價值；非理性的情緒為投資人對資產價格產生過度的預期，使資產價格偏離其內含價值。

過去研究崩盤與泡沫實證文章已證實投資人的行為面為促使股票泡沫及崩盤之重要因素，但在關於預測極端報酬的文獻中，卻都只以基本面作為預測的工具。本研究從行為財務學的角度出發以文字輿情與投資人關注度建構情緒指標，並將其區分為理性與非理性後，更能真實地刻畫、反映市場當下情況，藉此來分析投資人情緒與極端報酬情況的關係。

此外，本研究檢驗市場投資人情緒對於極端漲與極端跌狀態是否存在不對稱性。本研究觀察各效應淨效果在投資人情緒對股價極端狀況的影響，有助於進一步瞭解投資人行為並預測極端股價變化。

In this study, I construct individual investors' sentiment index, distinguish the rational component and irrational component, and use machine learning to predict the extreme rise and fall of individual stocks. We also examine in detail whether the asymmetric effect exists between investors' sentiment and extreme stock returns. Investor sentiment means the actions investors may take based on his or her perception of asset price changes from the observation of certain information. We argue that sentiment can have rational and irrational components. The rational sentiment is the investor's unbiased reaction to information, which makes the stock price reflect its intrinsic value. The irrational sentiment is the investor's excessive expectation of asset price, which leads to a deviation of asset prices from intrinsic value.
Past empirical research on crashes and bubbles has confirmed that investors' behavior is an important factor, but in the literature on predicting extreme return, only fundamentals are used as predictive tools. This study starts from the perspective of behavioral finance with text mining and investor attention and decomposes sentiment into rational and irrational components.
In addition, this study also tests the asymmetry effects between investor sentiment and stock extreme return, which helps to further understand investor behavior and predict extreme stock price changes.

論文審定書 i
摘要 ii
ABSTRACT iii
CONTENTS iv
LIST OF FIGURES vi
LIST OF TABLES vii
CHAPTER 1 INTRODUCTION 1
1.1 Background and Motivation 1
1.2 Purposes 9
1.3 Contribution 10
CHAPTER 2 LITERATURE REVIEW 12
2.1 Behavioral Finance 12
2.1.1 Rational and Irrational Sentiment 12
2.1.2 Investors’ Attention and Herding Effect 14
2.1.3 Technical Analysis and Heterogeneous Investment Behavior 15
2.1.4 Summary 16
2.2 Stock Extreme Return Situations 16
2.3 Machine Learning Models 17
CHAPTER 3 METHODOLOGY 20
3.1 Data 20
3.2 Extreme Return Condition 20
3.3 Construction of Sentiment Index 22
3.3.1 Text Mining 22
3.3.2 Google Search Volume Index 24
3.3.3 Investor Attention 24
3.4 Decompose the Sentiment Index 25
3.5 Word Vectorization Analysis 26
3.6 Behavioral Factor 28
3.7 Network Construction 30
3.7.1 Degree Centralization 31
3.7.2 Modularity 32
3.8 Forecast of Extreme Stock Situations 33
3.8.1 Logistic Regression 33
3.8.2 Extreme Gradient Boosting 34
CHAPTER 4 EMPIRICAL RESULTS 36
4.1 Descriptive Statistics 36
4.1.1 Extreme Stock Situations 36
4.1.2 Sentiment Component Variables Descriptive Statistics 39
4.1.3 Sentiment Index Descriptive Statistics 42
4.2 Relationship Between Sentiment and Market 45
4.3 Relationship Among Rational / Irrational and Market 49
4.4 Extreme Stock Return Situations Prediction 54
4.4.1 Logistic Regression 54
4.4.2 Extreme Gradient Boosting 60
4.4.3 Strategy Backtest 69
CHAPTER 5 CONCLUSION 70
REFERENCES 73

Abreu, Dilip, and Markus K. Brunnermeier. "Bubbles and crashes." Econometrica 71.1 (2003): 173-204.
Barberis, Nicholas, Andrei Shleifer, and Robert Vishny. "A model of investor sentiment1." Journal of financial economics 49.3 (1998): 307-343.
Brown, Gregory W., and Michael T. Cliff. "Investor sentiment and asset valuation." The Journal of Business 78.2 (2005): 405-440.
Baker, Malcolm, and Jeffrey Wurgler. "Investor sentiment and the cross‐section of stock returns." The journal of Finance 61.4 (2006): 1645-1680.
Creamer, Germán, and Yoav Freund. "Predicting performance and quantifying corporate governance risk for latin american adrs and banks." (2004).
Cornelli, Francesca, David Goldreich, and Alexander Ljungqvist. "Investor sentiment and pre‐IPO markets." The Journal of Finance 61.3 (2006): 1187-1216.
Chuang, Wu-Jen, Liang-Yuh Ouyang, and Wen-Chen Lo. "The impact of investor sentiment on excess returns a Taiwan stock market case." International Journal of Information and Management Sciences 21.1 (2010): 13-28.
De Bondt, Werner FM, and Richard Thaler. "Does the stock market overreact?." The Journal of finance 40.3 (1985): 793-805.
Da, Zhi, Joseph Engelberg, and Pengjie Gao. "In search of fundamentals." (2011).
Elton, Edwin J., Martin J. Gruber, and Jeffrey A. Busse. "Do investors care about sentiment?." The Journal of Business 71.4 (1998): 477-500.
Fauzi, Rizaldi, and Imam Wahyudi. "The effect of firm and stock characteristics on stock returns: Stock market crash analysis." The Journal of Finance and Data Science 2.2 (2016): 112-124.
Geske, Robert, and Richard Roll. "The fiscal and monetary linkage between stock returns and inflation." The journal of Finance 38.1 (1983): 1-33.
Hsieh, Shu-Fan. "Individual and institutional herding and the impact on stock returns: Evidence from Taiwan stock market." International Review of Financial Analysis 29 (2013): 175-188.
Joseph, Kissan, M. Babajide Wintoki, and Zelin Zhang. "Forecasting abnormal stock returns and trading volume using investor sentiment: Evidence from online search." International Journal of Forecasting 27.4 (2011): 1116-1127.
Liew, Jim Kyung-Soo, and Garrett Zhengyuan Wang. "Twitter sentiment and ipo performance: A cross-sectional examination." Journal of Portfolio Management 42.4 (2016): 129.
Nasseh, Alireza, and Jack Strauss. "Stock prices and domestic and international macroeconomic activity: a cointegration approach." The Quarterly Review of Economics and Finance40.2 (2000): 229-245.
Odean, Terrance. "Do investors trade too much?." American economic review 89.5 (1999): 1279-1298.
Piotroski, Joseph D. "Value investing: The use of historical financial statement information to separate winners from losers." Journal of Accounting Research (2000): 1-41.
Patel, Jigar, et al. "Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques." Expert Systems with Applications42.1 (2015): 259-268.
Roger E.A. Farmer,(2012),‘The stock market crash of 2008 caused the Great Recession: Theory and evidence.’, Journal of Economic Dynamics and Control, Elsevier, vol. 36(5), pages 693-707.
Shiller, Robert J. "The use of volatility measures in assessing market efficiency." The Journal of Finance 36.2 (1981): 291-304.
Shefrin, Hersh, and Meir Statman. "The disposition to sell winners too early and ride losers too long: Theory and evidence." The Journal of finance 40.3 (1985): 777-790.
Shiller, Robert J. "Measuring bubble expectations and investor confidence." The Journal of Psychology and Financial Markets1.1 (2000): 49-60.
Tetlock, Paul C. "Giving content to investor sentiment: The role of media in the stock market." The Journal of finance 62.3 (2007): 1139-1168.
Tai Ma, Kuo Lee, Chien Lai and Yang Lee. “Rational or Irrational? A Comprehensive Studies on Stock Market Crashes.” SSRN (2017)
Westerhoff, Frank, and Stefan Reitz. "Commodity price dynamics and the nonlinear market impact of technical traders: empirical evidence for the US corn market." Physica A: Statistical Mechanics and its Applications 349.3-4 (2005): 641-648.
Wang, Jia, Gulser Meric, Zugang Liu, and Ilhan Meric.,(2009),‘Stock market crashes, firm characteristics, and stock returns’,Journal of Banking and Finance, 33(9), pp. 1563-1574
Zhi Da, Joseph Engelberg, Pengjie Gao,(2011),‘In Search of Attention’,Journal of Finance, View issue TOC, Volume 66, Issue 5, October 2011, Pages 1461– 1499
Zouaoui, Mohamed, Genevieve Nouyrigat, and Francisca Beer. "How does investor sentiment affect stock market crises? Evidence from panel data." Financial Review 46.4 (2011): 723-747.