Work

GNN-based social media sentiment analysis for stock market forecasting and trading

Year: 2025

Type: article

Abstract: This study introduces a novel approach that utilises graph neural networks (GNNs) for sentiment analysis to enhance stock market predictions. By integrating social media sentiment analysis with traditional financial indicators, we develop a comprehensive model that accurately captures market sentiment dynamics. Our methodology includes data collection from social media platforms, sentiment extraction using GNN and natural language processing (NLP), and prediction using advanced time-series models such as LSTM, CNN and Transformer. We evaluate our model on several stock datasets and demonstrate improvements in both prediction accuracy and trading performance compared to traditional models. These results underscore the value of merging sentiment analysis with time-series techniques for financial market prediction. This work contributes to the field by providing insights into the role of sentiment in financial markets and by advancing the capabilities of predictive models through the integration of GNN-based sentiment analysis.

Source: Expert Systems with Applications

DOI: 10.1016/j.eswa.2025.128425

Authors: Pengju Zhang, Richard D.F. Harris, Jin Zheng

Institution: University of Bristol

Language: English

Topic: Stock Market Forecasting Methods

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: hybrid

Estimated APC paid: $3,500

Funder: University of Bristol