Stand for Something or Fall for Everything: Predict Misinformation Spread with Stance-Aware Graph Neural Networks
This addresses the pressing challenge of misinformation dissemination on social media platforms, offering an effective predictive model for intervention.
The paper tackles the problem of predicting misinformation spread on social media by proposing a stance-aware graph neural network that leverages users' stances, achieving a 32.65% improvement over benchmarks and 4.69% over advanced GNNs without stance information.
Although pervasive spread of misinformation on social media platforms has become a pressing challenge, existing platform interventions have shown limited success in curbing its dissemination. In this study, we propose a stance-aware graph neural network (stance-aware GNN) that leverages users' stances to proactively predict misinformation spread. As different user stances can form unique echo chambers, we customize four information passing paths in stance-aware GNN, while the trainable attention weights provide explainability by highlighting each structure's importance. Evaluated on a real-world dataset, stance-aware GNN outperforms benchmarks by 32.65% and exceeds advanced GNNs without user stance by over 4.69%. Furthermore, the attention weights indicate that users' opposition stances have a higher impact on their neighbors' behaviors than supportive ones, which function as social correction to halt misinformation propagation. Overall, our study provides an effective predictive model for platforms to combat misinformation, and highlights the impact of user stances in the misinformation propagation.