Stock Return Prediction with Financial and Textual Sentiment Factors: Evidence from the Chinese A-share Market

DOI

10.2991/978-94-6239-604-3_22How to use a DOI?

Keywords

stock returns; textual sentiment factors; Chinese A-share Market

Abstract

This paper investigates the predictive power of financial and textual sentiment factors on stock returns in the Chinese A-share market. Using monthly data from 2018 to 2024, the study combines standard financial indicators, such as size, book-to-market ratio, ROE, momentum, and volatility, with a sentiment factor derived from financial headlines. Three models are employed to predict stock returns: ordinary least squares (OLS), Lasso regression, and extreme gradient boosting (XGBoost). Performance is evaluated based on out-of-sample prediction accuracy and portfolio backtests. Empirically, include sentiment improves both statistical fit and economic value. That is, the model augmented with sentiment improves statistical fit over a financial-only model, and improved economic value over a statistical-only model in terms of forecast accuracy and portfolio returns. These results suggest the importance of behavioral and textual information for asset pricing and provide relevant insights for quantitative investing methods and financial technology in emerging economies.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yusha Wang
PY  - 2026
DA  - 2026/02/26
TI  - Stock Return Prediction with Financial and Textual Sentiment Factors: Evidence from the Chinese A-share Market
BT  - Proceedings of the 5th International Conference on Economic Development and Business Culture (ICEDBC 2025)
PB  - Atlantis Press
SP  - 200
EP  - 205
SN  - 2352-5428
UR  - https://doi.org/10.2991/978-94-6239-604-3_22
DO  - 10.2991/978-94-6239-604-3_22
ID  - Wang2026
ER  -