Graph global attention network with memory: A deep learning approach for fake news detection

Qian Chang, Xia Li, Zhao Duan

Abstract: Highlights•Our approach combines two strategies: a novel global attention mechanism with memory to capture structural homogeneity within news propagation networks, and a module for partial key information learning aggregation to emphasize crucial information acquisition in the graph.•The proliferation of social media has raised concerns about the detection of fake news, posing a significant threat to society and information credibility.•Our proposed method provides a new direction in news detection research, offering a comprehensive combination of global and partial information.•Extensive experiments on real-world datasets demonstrate the promising performance of GANM in accurately identifying fake news instances.•The GANM framework shows potential for enhancing social media platforms' ability to combat the dissemination of fake information and protect the credibility of information sources.