The content discusses the challenges of detecting rumors on social media and proposes a new detection model that combines user correlation and information propagation representations. The proposed model outperforms existing methods in detecting rumors, especially in early detection scenarios. The paper outlines the system design, including user feature encoding, text encoding, user correlation representation, information propagation representation, rumor classification with joint representations, and model training. Evaluation results on two public datasets demonstrate the effectiveness of the proposed model.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Tianrui Liu,... at arxiv.org 03-26-2024
https://arxiv.org/pdf/2403.16206.pdfDeeper Inquiries