With the vigorous development of information technology, the textual data of financial news have grown massively, and this ever-rich online news information can influence investors’ decision-making behavior, which affects the stock market. Thus, online news is an important factor affecting market volatility. Quantifying the sentiment of news media and applying it to stock-market prediction has become a popular research topic. In this study, a financial news sentiment lexicon and an auxiliary lexicon applicable to the financial field are constructed, and a sentiment index (SI) is constructed by defining the weight of semantic rules. Then, a comprehensive sentiment index (CSI) is constructed via principal component analysis of the sentiment index and structured stock-market trading data. Finally, these two sentiment indices are added to the generalized autoregressive conditional heteroscedastic (GARCH) and the Long short-term memory (LSTM) models to predict stock returns. The results indicate that the prediction results of LSTM models are better than those of GARCH models. Compared with general-purpose lexicons, the financial lexicons constructed in this study are more stable, and the inclusion of a comprehensive investor sentiment index improves the accuracy of measuring sentiment information. Thus, the proposed lexicons allow more comprehensive measurement of the effects of external sentiment factors on stock-market returns and can improve the prediction effect of stock-return models.

1. [1] V. Niederhoffer, “The Analysis of World Events and Stock Prices,” The J. of Business, Vol.44, No.2, pp. 193-219, 1971.
2. [2] P. C. Tetlock, “Giving Content to Investor Sentiment: The Role of Media in the Stock Market,” The J. of Finance, Vol.62, No.3, pp. 1139-1168, 2007.
3. [3] J. You and J. Wu, “Spiral of Silence: Media Sentiment and the Asset Mispricing,” Economic Research, Vol.47, pp. 141-152, 2012.
4. [4] X.-X. Cheng, “Contextual Effect or Content Effect? Empirical Test of Financial News and Online Public Opinion on Stock Market Quotation,” Statistics & Information Tribune, Vol.34, pp. 69-75, 2019.
5. [5] P. C. Tetlock, “Giving Content to Investor Sentiment: The Role of Media in the Stock Market,” The J. of Finance, Vol.62, No.3, pp. 1139-1168, 2007.
6. [6] C. Wang and J. Wu, “Media Tone Investor Sentiment and IPO Pricing,” J. of Financial Research, Vol.9, pp. 174-189, 2015.
7. [7] G. Tan, F. Jiang, and D. Zhang, “Progress on Text Sentiment in Financial Markets,” Economics Information, Vol.11, pp. 137-147, 2016.
8. [8] J. Bollen, H. Mao, and X. Zeng, “Twitter Mood Predicts the Stock Market,” J. of Computational Science, Vol.2, No.2, pp. 1-8, 2011.
9. [9] D. Lin and B. Chan, “A Statistical Study of the Impact of Online Public Opinion on Stock Prices Based on Investor Sentiment,” Southwest University of Finance and Economics, 2013.
10. [10] Z. Teng, “Media Sentiment: Information Interpretation and Market Stability,” Financial Regulation Research, Vol.5, pp. 32-53, 2018.
11. [11] R. Xiong, E. P. Nichols, and Y. Shen, “Deep Learning Stock Volatility with Google Domestic Trends,” arXiv preprint, arXiv:1512.04916, 2015.
12. [12] R. Akita, A. Yoshihara, T. Matsubara et al., “Deep learning for stock prediction using numerical and textual information,” Proc. of the 2016 IEEE/ACIS 15th Int. Conf. on Computer and Information Science,” IEEE, 2016.
13. [13] L. Persio and O. Honchar, “Recurrent Neural Networks Approach to the Financial Forecast of Google Assets,” Int. J. of Mathematics and Computers in Simulation, Vol.11, pp. 7-13, 2017.
14. [14] W. Chen and G. Xu, “A Study of Stock Market Volatility Prediction Accuracy Based on Deep Learning and Stock Forum Data,” Management World, Vol.34, pp. 180-181, 2018.
15. [15] Y. Wu and M. Chen, “Research and application of fine-grained sentiment analysis of financial microblogs,” South China University of Technology, 2018.
16. [16] Y.-S. Zang, “Adverbial Studies in Modern Chinese,” Xuelin Press, 2000 (in Chinese).
17. [17] W. Antweiler and M. Z. Frank, “Is all That Talk Just Noise? The Information Content of Internet Stock Message Boards,” The J. of Finance, Vol.59, No.3, pp. 1259-1294, 2004.
18. [18] Y.-Z. Yao, J.-Q. Wang, and Z.-F. Liu, “Mixed-frequency investor sentiment and stock price behavior,” J. of Management Sciences in China, Vol.21, pp. 104-113, 2018.
19. [19] T. Bollerslev, “Generalized Autoregressive Conditional Heteroskedasticity,” J. of Econometrics, Vol.31, No.3, pp. 307-327, 1986.
20. [20] M. Sundermeyer, R. Schlüter, and H. Ney, “LSTM Neural Networks for Language Modeling,” 13th Annual Conf. of the Int. Speech Communication Association (INTERSPEECH 2012), pp. 194-197, 2012.