郑州大学学报（理学版）2025，Vol.57Issue(3)：12-18,7.DOI:10.13705/j.issn.1671-6841.2024092
基于BGMA模型社交媒体虚假新闻检测研究
Research on Fake News Detection in Social Media Based on BGMA Model
摘要
Abstract
In order to identify fake news on social media platforms timely and accurately,a BGMA fake news detection model was constructed.The BGMA model at first used the BERT model to extract the se-mantic features of the textual content,and then the GAT model was used to capture the complex associa-tions and dynamic changes between user behaviors.Finally,the two features were weighted and fused by introducing a multi-attention mechanism.The results showed that the detection performance of the BGMA model could improves the accuracy by 4.06％on the PolitiFact dataset and 19.73％on the GossipCop dataset compared with the BERT-LSTM model.Compared with the GCNFC model,the accuracy was im-proved by 10.59％on the PolitiFact dataset and 10.47％on the GossipCop dataset.The practical test re-sult proved that the BGMA model could effectively combine text and user features and achieve better fake news detection results.关键词
虚假新闻检测/图注意力网络/多头注意力Key words
fake news detection/graph attention network/multi-head attention分类
计算机与自动化引用本文复制引用
王军,马小越,付红静..基于BGMA模型社交媒体虚假新闻检测研究[J].郑州大学学报（理学版）,2025,57(3):12-18,7.基金项目
河南省科技攻关项目(222102210292) （222102210292）
河南省科技智库调研项目(HNKJZK-2021-61C) （HNKJZK-2021-61C）
