基于在线社交网络的虚假新闻检测方法综述  

A Survey on Fake News Detection Based on Online Social Networks

作　　者：杨思佳 李显勇 杜亚军 YANG Sijia;LI Xianyong;DU Yajun(School of Computer and Software Engineering,Xihua University,Chengdu 610039 China;Yibin Weite Ruian Technology Co.,Ltd.,Yibin 644600 China)

机构地区：[1]西华大学计算机与软件工程学院,四川成都610039 [2]宜宾维特瑞安科技有限公司,四川宜宾644600

出　　处：《西华大学学报(自然科学版)》2025年第3期37-46,60,共11页Journal of Xihua University:Natural Science Edition

基　　金：国家自然科学基金(61802316);四川省科技计划资助(2022YFG0378,2023YFS0424,2023YFH0058,2023YFQ0044);宜宾市科技计划重点研发项目(2023SF004)。

摘　　要：在线社交网络承载着人民日益增长的社会交流需求,是现代重要的信息共享途径。随着社交网络的普及,在线社交网络也逐渐成了虚假新闻滋生的温床。虚假新闻的危害程度之深、范围之广,使得虚假新闻检测成为自然语言处理领域的热点研究之一。文章首先介绍了虚假新闻的相关概念及问题描述,然后基于内部特征和外部特征对虚假新闻检测方法进行综述,指出虚假新闻检测在即时检测、数据获取、类不平衡、旧谣新传等方面仍面临着挑战,未来应加强即时虚假新闻检测、多模态和可解释的虚假新闻检测、多语言和跨文化的虚假新闻检测等方面的研究。Online social networks have become increasingly popular as a means of social communica-tion and sharing information in the digital era.The growing demand for social interaction has resulted in the spread of fake news on social media platforms.The depth and wide scope of the harm of fake news have made its detection one of the hot research topics in natural language processing.The article first introduces the relevant concepts and issues of fake news,then reviews methods for detecting fake news based on in-ternal and external characteristics.It points out that fake news detection still faces challenges in real-time detection,data acquisition,class imbalance,and the spread of old rumors.Future research should focus on enhancing real-time fake news detection,multimodal and interpretable fake news detection,as well as mul-tilingual and cross-cultural fake news detection.

关 键 词：在线社交网络 虚假新闻检测 深度学习 特征提取 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]