From text to trade: harnessing the potential of generative AI for investor sentiment analysis in financial markets through large language models

From text to trade: harnessing the potential of generative AI for investor sentiment analysis in financial markets through large language models

연구 분야: Artificial Intelligence

학회: International Journal of Information Technology

This study explores the integration of generative artificial intelligence (AI) into financial sentiment analysis, focusing on enhancing market behavior predictions using advanced large language models (LLMs). A novel sentiment analysis framework is developed, leveraging cutting-edge LLMs and generative AI for data augmentation. The approach incorporates optimized word embeddings and fine-tuning techniques such as Few-shot Learning and Low-Rank Adaptation (LoRA) to handle the linguistic complexities of financial discourse. The framework is evaluated using five performance metrics, demonstrating improved accuracy and efficiency. These findings highlight the transformative potential of LLMs in financial decision-making and sentiment-driven trading strategies.