Event Study and Principal Component Analysis Based on Sentiment Analysis – A Combined Methodology to Study the Stock Market with an Empirical Study

This paper provides an improved method by introducing Sentiment Analysis into the Event Study and Principal Component Analysis. The model is constructed by using the heuristic mean-end analysis. This method enables us to take into investors’ feelings towards related stocks when we study the stock market’s reaction to a given event. This paper investigates the Chinese A-shared market over 2013–2019 to study the influence of rumors and the offsetting impact of rumor clarifications on the stock price. The results indicate that no matter investor sentiment is bullish or bearish, stock price reacts significantly to rumors before as well as when the rumor goes public. Furthermore, clarification offsets the positive abnormal returns caused by rumors with bullish sentiment substantially at a limited level. Still, after five days, it creates a positive effect like the positive rumor does on the stock price. Under the bearish sentiment, clarification brings an insignificant impact on the stock price. The results indicate that the source of rumor may not come from the media and investment decisions established on rumors would be beneficial to investors before as well as after they are published. Moreover, official clarification causes an offset effect, but it is very limited.

[1]  R. E. Diefenbach.  How Good is Institutional Brokerage Research , 1972 .

[2]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[3]  Dennis E. Logue,et al.  Brokerage House Investment Advice , 1973 .

[4]  Ghazaleh Beigi,et al.  An Overview of Sentiment Analysis in Social Media and Its Applications in Disaster Relief , 2016, Sentiment Analysis and Ontology Engineering.

[5]  Halil Kiymaz.  The effects of stock market rumors on stock prices: evidence from an emerging market , 2001 .

[6]  John B. Kaneene,et al.  An explanation of the use of principal-components analysis to detect and correct for multicollinearity , 1992 .

[7]  Leif E. Peterson.  K-nearest neighbor , 2009, Scholarpedia.

[8]  Rajesh Aggarwal,et al.  Stock Market Manipulation - Theory and Evidence , 2003 .

[9]  Trevor Hastie,et al.  Multi-class AdaBoost ∗ , 2009 .

[10]  J. Ross Quinlan,et al.  Learning decision tree classifiers , 1996, CSUR.

[11]  Yongli Luo,et al.  Rumor Clarification and Stock Returns: Do Bull Markets Behave Differently from Bear Markets? , 2014 .

[12]  S. P. Kothari,et al.  Econometrics of Event Studies , 2007 .

[13]  Stan Matwin,et al.  Large Scale Text Classification using Semisupervised Multinomial Naive Bayes , 2011, ICML.

[14]  Kenneth R. Ahern,et al.  Rumor Has It: Sensationalism in Financial Media , 2014 .

[15]  Michael Canes,et al.  Stock Prices and the Publication of Second-Hand Information , 1978 .

[16]  Gur Huberman,et al.  Contagious Speculation and a Cure for Cancer: A Nonevent that Made Stock Prices Soar , 2001 .

[17]  Li Chen,et al.  News impact on stock price return via sentiment analysis , 2014, Knowl. Based Syst..

[18]  E. Fama.  EFFICIENT CAPITAL MARKETS: A REVIEW OF THEORY AND EMPIRICAL WORK* , 1970 .

[19]  E. Fama,et al.  Efficient Capital Markets : II , 2007 .

[20]  Olivia Sheng,et al.  Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Future Stock Price Directional Movement , 2011, ICIS.

[21]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[22]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[23]  Jeonghee Yi,et al.  Sentiment analysis: capturing favorability using natural language processing , 2003, K-CAP '03.

[24]  Douglas C. Montgomery,et al.  Introduction to Linear Regression Analysis, Solutions Manual (Wiley Series in Probability and Statistics) , 2007 .