Unleashing Expert Opinion from Social Media for Stock Prediction

2025-04-14

AI Summary

To address the limitations of sparse expert signals (covering only 4% of stock-day instances) and high noise levels in social media for stock prediction, this paper proposes a novel framework integrating dynamic expert identification with cross-stock signal propagation. First, a dynamic expert tracking algorithm is designed to accurately identify high signal-to-noise ratio contrarian and consensus experts from platforms such as StockTwits. Second, a Dual Graph Attention Network (DualGAT) is introduced to jointly model expert–stock and stock–stock relational graphs, enabling effective diffusion of expert sentiment across correlated stocks. Combined with social sentiment modeling and multi-source feature fusion, the proposed model achieves state-of-the-art performance on both stock price trend and return forecasting tasks—outperforming baselines in accuracy, Sharpe ratio, and correlation between predicted and realized returns. Crucially, expert signals demonstrate independent predictive power and yield significant synergistic gains when combined with traditional financial factors.

Technology Category

• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community
• Machine Learning: Mixture of Experts (MoE)
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

While stock prediction task traditionally relies on volume-price and fundamental data to predict the return ratio or price movement trend, sentiment factors derived from social media platforms such as StockTwits offer a complementary and useful source of real-time market information. However, we find that most social media posts, along with the public sentiment they reflect, provide limited value for trading predictions due to their noisy nature. To tackle this, we propose a novel dynamic expert tracing algorithm that filters out non-informative posts and identifies both true and inverse experts whose consistent predictions can serve as valuable trading signals. Our approach achieves significant improvements over existing expert identification methods in stock trend prediction. However, when using binary expert predictions to predict the return ratio, similar to all other expert identification methods, our approach faces a common challenge of signal sparsity with expert signals cover only about 4% of all stock-day combinations in our dataset. To address this challenge, we propose a dual graph attention neural network that effectively propagates expert signals across related stocks, enabling accurate prediction of return ratios and significantly increasing signal coverage. Empirical results show that our propagated expert-based signals not only exhibit strong predictive power independently but also work synergistically with traditional financial features. These combined signals significantly outperform representative baseline models in all quant-related metrics including predictive accuracy, return metrics, and correlation metrics, resulting in more robust investment strategies. We hope this work inspires further research into leveraging social media data for enhancing quantitative investment strategies. The code can be seen in https://github.com/wanyunzh/DualGAT.

Problem

• Filter noisy social media posts for stock prediction
• Identify true and inverse experts for trading signals
• Propagate expert signals across stocks using dual graph network

Innovation

• Dynamic expert tracing algorithm filters noisy posts
• Dual graph attention network propagates expert signals
• Combines expert signals with traditional financial features