Employing Chinese A-share market data, this study explores how news text and economic policy uncertainty (EPU) can be combined to predict a company’s unanticipated earnings using the XL (extra long) Transformer and long short term memory (LSTM) models. The results show that adding news text features or the EPU index can improve the model’s predictive performance. However, adding the EPU index improves the model prediction performance by a tiny amount. Next, news headlines have better predictive performance relative to news content. Meanwhile, as a supplement to news headlines, news content can further improve predictive performance. Finally, the XL-Transformer model has better predictive performance than the LSTM model, but the improvement in the effect is limited.

1. [1] R. Ball and P. Brown, “An empirical evaluation of accounting income numbers,” J. of Accounting Research, Vol.6, No.2, pp. 159-178, 1968. https://doi.org/10.2307/2490232
2. [2] J. Livnat and R. R. Mendenhall, “Comparing the post-earnings announcement drift for surprises calculated from analyst and time series forecasts,” J. of Accounting Research, Vol.44, No.1, pp. 177-205, 2006. https://doi.org/10.1111/j.1475-679X.2006.00196.x
3. [3] C. Truong, “Post-earnings announcement abnormal return in the Chinese equity market,” J. of Int. Financial Markets, Institutions and Money, Vol.21, No.5, pp. 637-661, 2011. https://doi.org/10.1016/j.intfin.2011.04.002
4. [4] H. H. Feng, Z. K. Ma, and Y. F. Wu, “An empirical study of PEAD in China’s A-share main board market,” Contemporary Economics, Vol.2015, No.7, pp. 10-16, 2015 (in Chinese).
5. [5] M. Dzielinski, “Measuring economic uncertainty and its impact on the stock market,” Finance Research Letters, Vol.9, No.3, pp. 167-175, 2012. https://doi.org/10.1016/j.frl.2011.10.003
6. [6] X. Meng, Y. Yang, and X. Zhao, “The research on financial news and stock market investment strategy—Based on text mining for financial website,” Review of Investment Studies, Vol.35, No.8, pp. 29-37, 2016 (in Chinese).
7. [7] H. Lv et al., “Relationship between financial news and stock market fluctuations,” Data Analysis and Knowledge Discovery, Vol.5, No.1, pp. 99-111, 2021 (in Chinese).
8. [8] S. R. Baker, N. Bloom, and S. J. Davis, “Measuring economic policy uncertainty,” The Quarterly J. of Economics, Vol.131, No.4, pp. 1593-1636, 2016. https://doi.org/10.1093/qje/qjw024
9. [9] A. Bonaime, H. Gulen, and M. Ion, “Does policy uncertainty affect mergers and acquisitions?,” J. of Financial Economics, Vol.129, No.3, pp. 531-558, 2018. https://doi.org/10.1016/j.jfineco.2018.05.007
10. [10] F. Zhou and S. Jia, “Economic policy uncertainty, investor sentiment and volatility of China’s stock market,” Financial Regulation Research, Vol.2019, No.8, pp. 101-114, 2019 (in Chinese). https://doi.org/10.13490/j.cnki.frr.2019.08.007
11. [11] A. Manela and A. Moreira, “News implied volatility and disaster concerns,” J. of Financial Economics, Vol.123, No.1, pp. 137-162, 2017. https://doi.org/10.1016/j.jfineco.2016.01.032
12. [12] W. Gu et al., “Research on the prediction model of the direction of financial market returns: Based on text big data method,” Statistical Research, Vol.37, No.11, pp. 68-79, 2020 (in Chinese). https://doi.org/10.19343/j.cnki.11-1302/c.2020.11.006
13. [13] T. Qi and H. Jiang, “Exploring stock price trend using Seq2Seq based automatic text summarization and sentiment mining,” Management Review, Vol.33, No.5, pp. 257-269, 2021 (in Chinese). https://doi.org/10.14120/j.cnki.cn11-5057/f.2021.05.014