Leveraging large language models to examine the interaction between investor sentiment and stock performance

Abstract

Understanding the relationship between investor sentiment and stock performance is crucial in dynamic financial markets. Existing researches often focus on financial news and stock prices, while studies on investor sentiment typically rely on traditional machine learning models that require extensive data labeling. Additionally, most researches focus on single stock indices, overlooking the impact of brand popularity. To address these gaps, this study proposes a novel framework to analyze the interaction between investor sentiment and stock performance, using Chinese Baijiu industry stocks as a case example. It further explores how brand popularity influences this relationship, offering insights for informed investment decisions through artificial intelligence technology. In this study, we leverage Generative Pre-trained Transformer 4 (GPT-4), a state-of-the-art black-box large language model, to process vast volumes of unstructured text data from stock forums. By employing in-context learning with human-labeled examples, GPT-4 generates weak labels that are subsequently used to fine-tune Large Language Model Meta AI (LLaMA), a smaller and more efficient open-source LLM from Meta AI, thereby enabling sentiment-driven decision-making in real-world scenarios. To construct a comprehensive sentiment indicator, we integrate both direct and indirect factors influencing sentiment and use principal component analysis to combine them effectively. To examine interaction between sentiment and stock yield, we apply the Granger causality test and vector autoregression models across stocks with different brand popularity levels. The results show that our framework achieves state-of-the-art performance investor sentiment analysis. Moreover, with brand popularity significantly amplifying the interaction between investor sentiment and stock yield, it leads to bidirectional Granger causality in highly popular brands.