Deep learning, textual sentiment, and financial market

Fuwei Jiang (), Yumin Liu (), Lingchao Meng () and Huajing Zhang ()
Additional contact information
Fuwei Jiang: Central University of Finance and Economics
Yumin Liu: Central University of Finance and Economics
Lingchao Meng: University of International Business and Economics
Huajing Zhang: Shandong Technology and Business University

Information Technology and Management, 2025, vol. 26, issue 4, No 1, 465 pages

Abstract: Abstract In this paper, we apply the BERT model, a cut-edging deep learning model, to construct a novel textual sentiment index in the Chinese stock market. By introducing the stock market returns as sentiment labels, our BERT model effectively extracts textual sentiment-related information useful for asset pricing. We find that the BERT-based sentiment has much greater predictive power for stock market returns than the traditional dictionary method as well as the Baker–Wurgler investor sentiment index both in and out of sample. The BERT-based sentiment shows strong predictive power during economic downturns and can significantly predict future macroeconomic conditions. Overall, our BERT model offers a better measure of textual investor sentiment, highlighting the potentially significant value of deep learning, AI, and FinTech in financial market.

Keywords: Textual sentiment; Deep learning; Sentiment dictionary; Asset pricing (search for similar items in EconPapers)
JEL-codes: C53 G11 G12 (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10799-024-00428-z Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:infotm:v:26:y:2025:i:4:d:10.1007_s10799-024-00428-z

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10799

DOI: 10.1007/s10799-024-00428-z

Access Statistics for this article

Information Technology and Management is currently edited by Raymond Patterson and Erik Rolland

More articles in Information Technology and Management from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().