JERAJournal of Electronic Research and Application2208-35022208-3510Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jera.v9i5.12198ArticleCorrelation Analysis Between Investor Sentiment and Stock Price Fluctuations Based on Large Language Modelshttps://artdesignp.com/journal/JERA/9/5/10.26689/jera.v9i5.12198RenGuohua,LuoZiyu,ZhangNaiwen,YangYichen2025952025-10-15The efficient market hypothesis in traditional financial theory struggles to explain the short-term irrational fluctuations in the A-share market, where investor sentiment fluctuations often serve as the core driver of abnormal stock price movements. Traditional sentiment measurement methods suffer from limitations such as lag, high misjudgment rates, and the inability to distinguish confounding factors. To more accurately explore the dynamic correlation between investor sentiment and stock price fluctuations, this paper proposes a sentiment analysis framework based on large language models (LLMs). By constructing continuous sentiment scoring factors and integrating them with a long short-term memory (LSTM) deep learning model, we analyze the correlation between investor sentiment and stock price fluctuations. Empirical results indicate that sentiment factors based on large language models can generate an annualized excess return of 9.3% in the CSI 500 index domain. The LSTM stock price prediction model incorporating sentiment features achieves a mean absolute percentage error (MAPE) as low as 2.72%, significantly outperforming traditional models. Through this analysis, we aim to provide quantitative references for optimizing investment decisions and preventing market risks.

Baker M, Wurgler J, 2006, Investor Sentiment and the Cross-section of Stock Returns. The Journal of Finance, 61(4): 1645–1680.

Zhu H, Lu X, Xue L, 2023, A BERT-Based Sentiment Analysis Model for Financial Texts. Journal of Shanghai University (Natural Science Edition), 29(01): 118–128.

Wang D, Liang Y, 2025, The Technological Foundations, Application Scenarios, and Risk Prevention of Large Language Models in Artificial Intelligence: Taking the Banking Industry as an Example. Journal of Dongbei University of Finance and Economics, (04): 17–30.

Lu M, 2024, Research on the Application Principles, Challenges, and Implementation Paths of Large Language Models in the Financial Sector. Journal of Chongqing Technology and Business University (Social Science Edition), 41(04): 1–12.

Liu M, Zhang L, Ping W, et al., 2025, Research on a Multi-Stage Network Public Opinion-Driven Group Consensus Decision-Making Method Based on Large Language Models. Chinese Journal of Management, 22(04): 750–759.

Jiang F, Liu Y, Meng L, 2024, Large Language Models, Text Sentiment, and Financial Markets. Management World, 40(08): 42–64.

Weng X, Lin X, Zhao S, 2022, A Long Short-Term Memory Network Stock Price Movement Prediction Model Based on Empirical Mode Decomposition and Investor Sentiment. Computer Applications, 42(S2): 296–301.

Yang S, Guo W, 2018, Investor Sentiment, Excess Returns, and Market Volatility. Journal of Hubei Engineering University, 38(02): 85–90.

Brown GW, Cliff MT, 2004, Investor Sentiment and the Near-Term Stock Market. Journal of Empirical Finance, 11(1): 1–27.

Xu T, 2018, Research on the Impact of Investor Sentiment on the Stock Market in Online Social Media. Shanghai Management Science, 40(03): 67–74.