Fake News Detection Based on Cross-Modal Message Aggregation and Gated Fusion Network

作     者：Fangfang Shan Mengyao Liu Menghan Zhang Zhenyu Wang 

作者机构：College of ComputerZhongyuan University of TechnologyZhengzhou450007China Henan Key Laboratory of Cyberspace Situation AwarenessZhengzhou450001China 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2024年第80卷第7期

页      面：1521-1542页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 08[工学] 081201[工学-计算机系统结构] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.62302540) with author Fangfang Shan.For more information,please visit their website at https://www.nsfc.gov.cn/(accessed on 31/05/2024) Additionally,it is also funded by the Open Foundation of Henan Key Laboratory of Cyberspace Situation Awareness(No.HNTS2022020) where Fangfang Shan is an author.Further details can be found at http://xt.hnkjt.gov.cn/data/pingtai/(accessed on 31/05/2024) supported by the Natural Science Foundation of Henan Province Youth Science Fund Project(No.232300420422) for more information,you can visit https://kjt.henan.gov.cn/2022/09-02/2599082.html(accessed on 31/05/2024) 

主　　题：Fake news detection cross-modalmessage aggregation gate fusion network co-attention mechanism multi-modal representation 

摘      要：Social media has become increasingly significant in modern society,but it has also turned into a breeding ground for the propagation of misleading information,potentially causing a detrimental impact on public opinion and daily *** to pure text content,multmodal content significantly increases the visibility and share ability of *** has made the search for efficient modality representations and cross-modal information interaction methods a key focus in the field of multimodal fake news *** effectively address the critical challenge of accurately detecting fake news on social media,this paper proposes a fake news detection model based on crossmodal message aggregation and a gated fusion network(MAGF).MAGF first uses BERT to extract cumulative textual feature representations and word-level features,applies Faster Region-based ConvolutionalNeuralNetwork(Faster R-CNN)to obtain image objects,and leverages ResNet-50 and Visual Geometry Group-19(VGG-19)to obtain image region features and global *** image region features and word-level text features are then projected into a low-dimensional space to calculate a text-image affinity matrix for cross-modal message *** gated fusion network combines text and image region features to obtain adaptively aggregated *** interaction matrix is derived through an attention mechanism and further integrated with global image features using a co-attention mechanism to producemultimodal ***,these fused features are fed into a classifier for news *** were conducted on two public datasets,Twitter and *** show that the proposed model achieves accuracy rates of 91.8%and 88.7%on the two datasets,respectively,significantly outperforming traditional unimodal and existing multimodal models.