Search

Analysis of the Time-Varying Effect of News Sentiment on Asset Pricing Based on Text Mining

Author(s)

Zhenkun He*, Jiawei Yan, Jundi Jing

Affiliation(s)

Xi'an Jiaotong-Liverpool University, Suzhou, Jiangsu, China *Corresponding Author.

Abstract

This study explores the dynamic impact mechanism of sentiment changes on asset prices based on text mining technology of news sentiment and Stata data analysis tools. By constructing a dynamic regression model and using rolling window estimation, the time-varying effect of sentiment fluctuations on asset prices is captured, revealing the short-term impact of sentiment on asset prices in different periods and its impact characteristics under different market conditions. The results show that extreme sentiment values are consistent with significant fluctuations in market prices. Changes in sentiment scores not only affect prices in the short term, but may also predict future market volatility trends. The case analysis of an unexpected interest rate hike further illustrates how sudden shifts in news sentiment can lead to immediate and pronounced market reactions, underscoring sentiment’s role in amplifying short-term volatility. By introducing sentiment factors, the model better depicts the irrational dynamic behavior of the market, helps explain market anomalies that are difficult to capture in traditional asset pricing models, and provides new perspectives and empirical support for asset pricing and investment decisions.

Keywords

News Sentiment; Asset Prices; Time-Varying Effects; Dynamic Regression Models; Stata Analysis

References

[1]Manzoor, N., Rai, D. S., Goswami, S.: Stock Exchange Prediction Using Financial News and Sentiment Analysis. Algorithms for Intelligent Systems (2021). [2]Li, X., Xie, H., Chen, L., Wang, J., Deng, X.: News impact on stock price return via sentiment analysis. Knowl. Based Syst., 69, 14-23 (2014). [3]Uhl, M. W., Pedersen, M., Malitius, O.: What’s in the News? Using News Sentiment Momentum for Tactical Asset Allocation. The Journal of Portfolio Management, 41, 100-112 (2015). [4]Fama, E., & French, K.: The Capital Asset Pricing Model: Theory and Evidence. S&P Global Market Intelligence Research Paper Series, (2003). [5]Çelik, Ş.: Theoretical and Empirical Review of Asset Pricing Models: A Structural Synthesis. Capital Markets: Asset Pricing & Valuation eJournal (2012). [6]Duffie, D.: Dynamic Asset Pricing Theory. Economics (1992). [7]Uhl, M. W., Pedersen, M., Malitius, O.: What’s in the News? Using News Sentiment Momentum for Tactical Asset Allocation. The Journal of Portfolio Management, 41, 100-112 (2015). [8]Kelly, S., & Ahmad, K.: Estimating the impact of domain-specific news sentiment on financial assets. Knowl. Based Syst., 150, 116-126 (2018). [9]Chandra, A., & Thenmozhi, M.: Behavioural Asset Pricing: Review and Synthesis. Journal of Interdisciplinary Economics, 29, 1-31 (2017). [10]Zhou, G., & Fabozzi, F.: General Principles of Asset Pricing. (2012). [11]Pitsillis, M.: Review of literature on multifactor asset pricing models. Elsevier (2005). [12]Rothschild, M.: Asset Pricing Theories. NBER Working Paper Series, 1985. [13]Fraiberger, S., Lee, D. Q., Puy, D., Rancière, R. G.: Media Sentiment and International Asset Prices. NBER Working Paper Series, 8649, 1-34 (2018). [14]Sridhar, S., Sanagavarapu, S.: Effect of Rate of Change of Stock Prices with News Sentiment Analysis. 2021 18th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE), 1-6 (2021). [15]Hafez, P. A., Xie, J.: News Beta: Factoring Sentiment Risk into Quant Models. The Journal of Investing, 25, 88-104 (2016). [16]Jiao, P., Veiga, A., Walther, A.: Social Media, News Media, and the Stock Market. Cognitive Social Science eJournal (2018). [17]Coqueret, G.: The Economic Value of Firm-Specific News Sentiment. Behavioral & Experimental Finance eJournal (2018). [18]Smales, L.: Time-Varying Relationship of News Sentiment, Implied Volatility, and Stock Returns. Applied Economics, 48, 4942-4960 (2012). [19]Allen, D., McAleer, M., Singh, A. K.: Daily Market News Sentiment and Stock Prices. Applied Economics, 51, 3212-3235 (2015). [20]Sadik, Z. A., Mitra, G., Tan, Z.: Asset Allocation Strategies: Enhanced by News. Behavioral & Experimental Finance eJournal (2020). [21]Shah, D., Isah, H., Zulkernine, F.: Predicting the Effects of News Sentiments on the Stock Market. 2018 IEEE International Conference on Big Data (Big Data), 4705-4708 (2018). [22]Rohner, P., Uhl, M. W.: Applying News Sentiment for Optimizing Strategic Asset Allocations. The Journal of Investing, 31, 24-37 (2021). [23]Pyo, D.-J., Kim, J.: News Media Sentiment and Asset Prices in Korea: Text-Mining Approach. Asia-Pacific Journal of Accounting & Economics, 28, 183-205 (2019). [24]Nassirtoussi, A. K., Aghabozorgi, S., Wah, T. Y., Ngo, D.: Text Mining of News-Headlines for FOREX Market Prediction: A Multi-layer Dimension Reduction Algorithm. Expert Syst. Appl., 42, 306-324 (2015). [25]Siering, M.: "Boom" or "Ruin"—Does It Make a Difference? Using Text Mining and Sentiment Analysis for Intraday Investment Decisions. Hawaii International Conference on System Sciences, 1050-1059 (2012). [26]Besimi, A., Dika, Z., Shehu, V., Selimi, M.: Applied Text-Mining Algorithms for Stock Price Prediction Based on Financial News Articles. Managing Global Transitions, 17, 335-351 (2019). [27]Ke, Z., Kelly, B., Xiu, D.: Predicting Returns with Text Data. Econometric Modeling: Capital Markets - Forecasting eJournal (2019). [28]Vanstone, B., Gepp, A., Harris, G.: Do News and Sentiment Play a Role in Stock Price Prediction? Applied Intelligence, 1-6 (2019). [29]Day, M.-Y., Lee, C.-C.: Deep Learning for Financial Sentiment Analysis on Finance News Providers. IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 1127-1134 (2016). [30]Cui, H., Zhu, Y., Gu, F., Wang, L.: Research on Stock Price Prediction Using TextRank Based Text Summarization Technology and Sentiment Analysis. International Conference on Computational Intelligence and Security (CIS), 302-306 (2022). [31]Shihabeldeen, H. Y. A.: Using Text Mining to Predicate Exchange Rates with Sentiment Indicators. Journal of Business Theory and Practice (2019). [32]Crone, S., Koeppel, C.: Predicting Exchange Rates with Sentiment Indicators: An Empirical Evaluation Using Text Mining. IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr), 114-121 (2014).