Dynamic Graph Neural Network for Fake News Detection

Abstract

The majority of existing propagation-based fake news detection algorithms are overwhelmingly depend on static networks, supposing the entire information propagation graph is readily available before performing fake news detection algorithms. However, real-world information diffusion networks are dynamic as new nodes joining the network and new edges being created. To deal with the problem, we proposed a dynamic propagation graph-based fake news detection method to capture the missing dynamic propagation information in static networks. Specifically, the proposed fake news detection algorithm models each news propagation graph as a series of graph snapshots recorded at discrete time stamps. We evaluate our approach on two bench datasets, and the experimental results demonstrate the effectiveness of the proposed method.