Impact of LLMs news Sentiment Analysis on Stock Price Movement Prediction

2026-01-22

AI Summary

This study addresses the limited understanding of how news sentiment influences stock price prediction and the lack of systematic evaluation of large language model (LLM) architectures for this task. The authors propose a framework that integrates LLM-derived news sentiment features with time-series forecasting models. They present the first systematic comparison of DeBERTa, RoBERTa, and FinBERT in financial sentiment analysis and investigate multi-model ensemble and cross-architecture fusion strategies. Experimental results show that DeBERTa alone achieves 75% accuracy, which improves to approximately 80% with a three-model ensemble. Furthermore, incorporating the extracted sentiment features consistently yields modest but reliable performance gains across diverse time-series models—including LSTM, PatchTST, tPatchGNN, and TimesNet—demonstrating the effectiveness and generalizability of sentiment information in financial forecasting.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models
• Computer Vision: Large Vision Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This paper addresses stock price movement prediction by leveraging LLM-based news sentiment analysis. Earlier works have largely focused on proposing and assessing sentiment analysis models and stock movement prediction methods, however, separately. Although promising results have been achieved, a clear and in-depth understanding of the benefit of the news sentiment to this task, as well as a comprehensive assessment of different architecture types in this context, is still lacking. Herein, we conduct an evaluation study that compares 3 different LLMs, namely, DeBERTa, RoBERTa and FinBERT, for sentiment-driven stock prediction. Our results suggest that DeBERTa outperforms the other two models with an accuracy of 75% and that an ensemble model that combines the three models can increase the accuracy to about 80%. Also, we see that sentiment news features can benefit (slightly) some stock market prediction models, i.e., LSTM-, PatchTST- and tPatchGNN-based classifiers and PatchTST- and TimesNet-based regression tasks models.

Problem

• LLM
• sentiment analysis
• stock price prediction
• news sentiment
• model evaluation

Innovation

• LLM-based sentiment analysis
• stock price prediction
• model ensemble
• financial time series
• DeBERTa