Search

Capital Market Group Sentiment Intelligent Measurement: An Empirical Study on Quantitative Investment Based on Psychological Perspective and LSTM

Author(s)

Katherine Lin Shu*

Affiliation(s)

Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK *Corresponding Author

Abstract

Behavioral finance has shed new light on how capital market group sentiment-an important non-fundamental factor-shapes asset pricing and investment returns. Traditional sentiment measurement methods, such as questionnaires and single-market indicator proxies, often fall short due to data lag, subjective bias, and incomplete coverage of key dimensions. To address these issues, we built a multi-dimensional group sentiment measurement framework rooted in psychological theory, and applied the Long Short-Term Memory (LSTM) neural network to enable intelligent sentiment prediction and refine quantitative investment strategies. First, we drew on core psychological theories to identify three fundamental dimensions: valence, arousal, and dominance. For each dimension, we integrated multi-source data-including textual content, market transaction records, and investor survey results-to develop quantitative indicators. Second, we used the LSTM model to capture the temporal dependence and dynamic changes of group sentiment, comparing its performance with traditional time-series models to verify its superiority in sentiment prediction. Finally, we designed a quantitative investment strategy based on the predicted sentiment index. Our findings reveal three key insights: (1) The multi-dimensional sentiment index based on psychological theory reflects actual capital market group sentiment more comprehensively; (2) Compared with traditional models, the LSTM model reduces prediction errors and effectively captures sentiment shocks caused by black swan events; (3) The LSTM-driven sentiment strategy achieves an annualized return 3.3 percentage points higher than the benchmark index, demonstrating strong risk-return performance. This research offers an innovative approach to intelligent capital market sentiment measurement and enriches the application of psychological theory.

Keywords

Capital Market; Group Sentiment; Psychological Perspective; LSTM Neural Network; Quantitative Investment; Sentiment Prediction

References

[1] Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383-417. [2] De Long, J. B., Shleifer, A., Summers, L. H., & Waldmann, R. J. (1990). Noise trader risk in financial markets. Journal of Political Economy, 98(4), 703-738. [3] Shiller, R. J. (2000). Irrational exuberance. Princeton University Press. [4] Brown, G. W., & Cliff, M. T. (2004). Investor sentiment and the near-term stock market. Journal of Empirical Finance, 11(1-2), 1-27. [5] Tetlock, P. C. (2007). Giving content to investor sentiment: The role of media in the stock market. The Journal of Finance, 62(3), 1139-1168. [6] Halder, S. (2022). Finbert-lstm: Deep learning based stock price prediction using news sentiment analysis. arxiv preprint arxiv:2211.07392. [7] Russell, J. A. (1980). A circumplex model of affect. Journal of Personality and Social Psychology, 39(6), 1161-1178. [8] Watson, D., & Tellegen, A. (1985). Toward a consensual structure of mood. Psychological Bulletin, 98(2), 219-235. [9] Bikhchandani, S., Hirshleifer, D., & Welch, I. (1992). A theory of fads, fashion, custom, and cultural change as informational cascades. Journal of Political Economy, 100(5), 992-1026. [10]Box, G. E., & Jenkins, G. M. (1976). Time series analysis: Forecasting and control. Holden-Day. [11]Fischer, T., & Krauss, C. (2018). Deep learning with long short-term memory networks for financial market predictions. European Journal of Operational Research, 270(2), 654-669. [12]Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. [13]Baker, M., & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. The Journal of Finance, 61(4), 1645-1680. [14]Baker, M., & Stein, J. C. (2004). Market liquidity as a sentiment indicator. Journal of Financial Markets, 7(3-4), 271-299. [15]Xie, H., Lin, W., Lin, S., Wang, J., & Yu, L. C. (2021). A multi-dimensional relation model for dimensional sentiment analysis. Information Sciences, 579, 832-844. [16]Mehrabian, A., & Russell, J. A. (1974). An approach to environmental psychology. MIT Press. [17]Kahneman, D., & Tversky, A. (1979). Prospect theory: An analysis of decision under risk. Econometrica, 47(2), 263-291. [18]Teng, X., Zhang, L., Gao, P., Yu, C., & Sun, S. (2025). BERT-Driven stock price trend prediction utilizing tokenized stock data and multi-step optimization approach. Applied Soft Computing, 170, 112627. [19]Kim, D. H., Kim, D. J., & Choi, S. Y. (2025). A Variational-Mode-Decomposition-Cascaded Long Short-Term Memory with Attention Model for VIX Prediction. Applied Sciences, 15(10), 5630. [20]Loewenstein, G. F., Weber, E. U., Hsee, C. K., & Welch, N. (2001). Risk as feelings. Psychological Bulletin, 127(2), 267-286.