TY - GEN
T1 - Stand for Something or Fall for Everything
T2 - 44th International Conference on Information Systems: Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies, ICIS 2023
AU - Chen, Zihan
AU - Sun, Jingyi
AU - Liu, Rong
AU - Mai, Feng
N1 - Publisher Copyright:
© 2023 International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Hu. All Rights Reserved.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - Echo Chamber
KW - Graph Neural Networks
KW - Misinformation Spread
KW - User Stance
UR - http://www.scopus.com/inward/record.url?scp=85192563026&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85192563026&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85192563026
T3 - International Conference on Information Systems, ICIS 2023: "Rising like a Phoenix: Emerging from the Pandemic and Reshaping Human Endeavors with Digital Technologies"
BT - International Conference on Information Systems, ICIS 2023
Y2 - 10 December 2023 through 13 December 2023
ER -