股市危机情境下社会媒体投资者情绪对股票市场的影响研究

摘要/Abstract

摘要： 本研究以2015年下半年中国股市经历的股市危机为背景，通过分层采样的方式选取沪深300指数成分股中60只股票作为样本，爬取样本企业相关的新浪微博文本并提取各类细分情绪，对该特殊时期社交媒体中不同细分情绪对股票市场的影响进行了评估。研究基于“情绪-认知-行为”框架，通过使用隐马尔可夫模型挖掘出“市场认知”这一认知层次上的隐含状态，进而建立投资者情绪与股票市场收益率的间接联系，试图还原真实的决策过程，发现最终影响股票市场的主要情绪。研究表明，股市危机中投资者情绪通过影响市场认知的方式间接影响股票市场，其中正面情绪对市场认知发挥积极的调整作用，而以“怒”为代表的负面高唤醒情绪会恶化市场认知进而加重危机的影响。该研究结论能够指导企业经营者在危机中做出科学的情绪疏导策略，以减弱危机中投资者情绪对市场的影响。此外，本研究为企业经营者和相关研究提供了一种通过挖掘市场隐含状态进而探究情绪和股票市场指标间影响关系的新思路。

关键词: 股市危机, 隐马尔可夫模型, 投资者情绪, 有序逻辑回归, 社交媒体

Abstract: Based on the background of a typical stock market crash for Chinese stock market in the second half of 2015, this study selects 60 stocks in the Shanghai and Shenzhen 300 Index stocks as a sample through stratified sampling, and crawls the Sina Weibo texts related to the company for calculating the multi-category emotion in social media (or investor sentiment). This study evaluates the impact of investor sentiment on stock market during crash period. Based on the “Emotion-Cognition-Behavior” framework, the study mines the hidden state of “market cognition” for the stock market by using Hidden Markov Model (HMM), and then establishes an indirect relationship between investor sentiment and stock return. The study discovers that investor sentiment indirectly affects the stock market by the market cognition. To be more specific, positive sentiment plays a positive role in adjusting market cognition, while negative sentiment with high arousal (e.g. “Anger”) will worsen the market cognition toward the crash state. The results guide business operators to make scientific emotional counseling strategies to reduce the impact of investor sentiment in social media on the market during the crash period. In addition, this study also provides a new approach for business operators to explore the relationship between sentiment and stock market indicators by hidden states mining.

Key words: stock market crash, Hidden Markov Model, investor sentiment, ordered-logistic regression, social media

裘江南, 葛一迪. 股市危机情境下社会媒体投资者情绪对股票市场的影响研究[J]. 管理评论, 2021, 33(5): 281-294.

Qiu Jiangnan, Ge Yidi. Research on the Influence of Emotion in Social Media on Stock Market in the Context of Stock Market Crash[J]. Management Review, 2021, 33(5): 281-294.

参考文献

[1] 刘成立. 股市危机中股指期货应该限制交易吗——基于2015年股市危机的实证分析[J]. 统计与信息论坛, 2017,32(1):84-93
[2] 杨丽,徐小雪,李炯华. 微博与企业危机公关管理研究[J]. 中国经贸导刊, 2011,(22):74-75
[3] 邓小龙,尹栾玉,李欲晓. 基于SPA模型的社会媒体信息传播机制建模与研究[J]. 管理评论, 2016,28(8):99-105
[4] 赖凯声,陈浩,乐国安,等. 情绪能预测股市吗?[J]. 心理科学进展, 2014,22(11):1770-1781
[5] Zouaoui M., Nouyrigat G., Beer F. How does Investor Sentiment Affect Stock Market Crises? Evidence from Panel Data[J]. Financial Review, 2011,46(4):723-747
[6] 赵汝为,熊熊,沈德华. 投资者情绪与股价崩盘风险:来自中国市场的经验数据[J]. 管理评论, 2019,31(3):50-60
[7] Irresberger F., Mühlnickel J., Weiß G. N. F. Explaining Bank Stock Performance with Crash Sentiment[J]. Journal of Banking & Finance, 2015,59:311-329
[8] 易志高,龚辉锋,茅宁. 分类思维、投资者情绪与股票价格联动[J]. 管理评论, 2014,26(4):22-30
[9] 于全辉,孟卫东. 牛熊市投资者情绪与上证综指的协整关系研究[J]. 预测, 2010,29(5):55-58
[10] De Long J. B., Shleifer A., Summers L. H., et al. Noise Trader Risk in Financial Markets[J]. Journal of Political Economy, 1990,98(4):703-738
[11] 池丽旭,庄新田. 我国投资者情绪对股票收益影响——基于面板数据的研究[J]. 管理评论, 2011,23(6):41-48
[12] Baker M., Wurgler J. The Equity Share in New Issues and Aggregate Stock Returns[J]. Journal of Finance, 2000,55(5):2219-2257
[13] Baker M., Stein J. C. Market Liquidity as a Sentiment Indicator[J]. Journal of Financial Markets, 2004,7(3):271-299
[14] 刘斌,胡菁芯,李涛. 投资者情绪、会计信息质量与股票收益[J]. 管理评论, 2018,30(7):36-46
[15] Edmans A., Garcia D., Norli O. Sports Sentiment and Stock Returns[J]. Journal of Finance, 2007,62(4):1967-1998
[16] Sanuders E. M. Stock Prices and Wall Street Weather[J]. The American Economic Review, 1998,83(3):1337-1345
[17] Gilbert E., Karahalios K. Widespread Worry and the Stock Market[C]. The 4th International AAAI Conference on Weblogss and Social Media, 2010
[18] Das S. R., Chen M. Y. Yahoo! For Amazon:Sentiment Extraction from Small Talk on the Web[J]. Management Science, 2007,53(9):1375-1388
[19] Tetlock P. C., Saar-Tsechansky M., Macskassy S. More than Words:Quantifying Language to Measure Firms' Fundamentals[J]. Journal of Finance, 2008, 63(3):1437-1467
[20] Da Z., Engelberg J., Gao P. In Search of Attention[J]. Journal of Finance, 2011,66(5):1461-1499
[21] 金秀,姜尚伟,苑莹. 基于股吧信息的投资者情绪与极端收益的可预测性研究[J]. 管理评论, 2018,30(7):18-27
[22] Yu Y., Duan W., Cao Q. The Impact of Social and Conventional Media on Firm Equity Value:A Sentiment Analysis Approach[J]. Decision Support Systems, 2013,55(4):919-926
[23] Kahneman D., Tversky A. Prospect Theory:An Analysis of Decision under Risk[J]. Econometrica, 1979,47(2):363-391
[24] Asur S., Huberman B. A. Predicting the Future with Social Media[J]. IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, 2010,7:492-499
[25] Robertson C. T., Dutton W. H., Ackland R., et al. The Democratic Role of Social Media in Political Debates:The Use of Twitter in the First Televised US Presidential Debate of 2016[J]. Journal of Information Technology & Politics, 2019,16(2):105-118
[26] Bollen J., Mao H., Zeng X. Twitter Mood Predicts the Stock Market[J]. Journal of Computational Science, 2011,2(1):1-8
[27] Zhang X., Fuehres H., Gloor P. A. Predicting Stock Market Indicators through Twitter "I Hope It Is Not as Bad as I Fear"[J]. Procedia-Social and Behavioral Sciences, 2011,26(1):55-62
[28] Zheludev I., Smith R., Aste T. When can Social Media Lead Financial Markets?[J]. Scientific Reports, 2014,4:4213
[29] Xun J., Guo B. Twitter as Customer's eWOM:An Empirical Study on Their Impact on Firm Financial Performance[J]. Internet Research, 2017,27(5):1014-1038
[30] Ho C. S., Damien P., Gu B., et al. The Time-varying Nature of Social Media Sentiments in Modeling Stock Returns[J]. Decision Support Systems, 2017,101:69-81
[31] Luo X., Zhang J., Duan W. Social Media and Firm Equity Value[J]. Information Systems Research, 2013,24(1):146-163
[32] Bartov E., Faurel L., Mohanram P. S. Can Twitter Help Predict Firm-level Earnings and Stock Returns?[J]. The Accounting Review, 2017,93(3):25-57
[33] Deng S., Huang Z., Sinha A. P., et al. The Interaction between Microblog Sentiment and Stock Return:An Empirical Examination[J]. MIS Quarterly, 2018,42(3):895-918
[34] Li D., Wang Y., Madden A., et al. Analyzing Stock Market Trends Using Social Media User Moods and Social Influence[J]. Journal of the Association for Information Science and Technology, 2019,70(9):1000-1013
[35] Gaspar R., Pedro C., Panagiotopoulos P., et al. Beyond Positive or Negative:Qualitative Sentiment Analysis of Social Media Reactions to Unexpected Stressful Events[J]. Computers in Human Behavior, 2016,56:179-191
[36] Wang B., Huang H., Wang X. A Novel Text Mining Approach to Financial Time Series Forecasting[J]. Neurocomputing, 2012,83:136-145
[37] Vu T. T., Chang S., Ha Q. T., et al. An Experiment in Integrating Sentiment Features for Tech Stock Prediction in Twitter[C]. Proceedings of the Workshop on Information Extraction and Entity Analytics on Social Media Data, 2012
[38] Li Q., Wang T. J., Li P., et al. The Effect of News and Public Mood on Stock Movements[J]. Information Sciences, 2014,278:826-840
[39] Nguyen N. Hidden Markov Model for Stock Trading[J]. International Journal of Financial Studies, 2018,6(2):36
[40] Baum L. E., Petrie T. Statistical Inference for Probabilistic Functions of Finite State Markov Chains[J]. Annals of Mathematical Statistics, 1966,37(6):1554-1563
[41] 胡淑兰,魏捷,黄晟. 基于隐马尔可夫模型的中国股市状态转换及预测[J]. 统计与决策, 2011,(22):152-154
[42] 徐琳宏,林鸿飞,潘宇,等. 情感词汇本体的构造[J]. 情报学报, 2008,27(2):180-185
[43] Gandhi P., Lustig H. Size Anomalies in U.S. Bank Stock Returns[J]. The Journal of Finance, 2015,70(2):733-768
[44] Aebi V., Sabato G., Schmid M. Risk Management, Corporate Governance, and Bank Performance in the Financial Crisis[J]. Journal of Banking & Finance, 2012,36(12):3213-3226
[45] 花贵如,郑凯,刘志远. 政府控制、投资者情绪与公司资本投资[J]. 管理评论, 2014,26(3):53-60
[46] Russell S. J., Norvig P., Davis E. 人工智能:一种现代的方法[M]. 北京:清华大学出版社, 2013
[47] Akaike H. A New Look at the Statistical Model Identification[J]. Automatic Control IEEE Transactions on, 1974,19(6):716-723
[48] Schwarz G. Estimating the Dimension of a Model[J]. The Annals of Statistics, 1978,6(2):461-464
[49] Dong Y., Chen H., Qian W., et al. Micro-blog Social Moods and Chinese Stock Market:The Influence of Emotional Valence and Arousal on Shanghai Composite Index Volume[J]. International Journal of Embedded Systems, 2015,7(2):148-155
[50] Chung W., Zeng D. Dissecting Emotion and User Influence in Social Media Communities:An interaction Modeling Approach[J]. Information & Management, 2018,9(8):1-16
[51] Zhao S., Chen X., Zhang J. The Systemic Risk of China's Stock Market during the Crashes in 2008 and 2015[J]. Physica A:Statistical Mechanics and its Applications, 2019,520:161-177