基于语义扩充和HDGCN的虚假新闻联合检测技术
Unified Fake News Detection Based on Semantic Expansion and HDGCN
张明道 1周欣 1吴晓红 1卿粼波 1何小海1
作者信息
- 1. 四川大学电子信息学院 成都 610065
- 折叠
摘要
虚假新闻检测的方法有很多种,单一的方法通常只关注新闻内容、社交上下文或外部事实等信息;而联合检测方法则通过整合多种模式信息达到检测目的.Pref-FEND即为一种整合新闻内容与外部事实的联合检测方法,它从新闻内容和外部事实中提取3种词语表示,利用动态图卷积网络获得词节点之间的关系.但其在如何让两种模式更加专注于自己的偏好部分方面仍存在不足.因此,对Pref-FEND模型进行了改进,利用语义挖掘扩充新闻中的风格词,利用实体链接扩充新闻中的实体词,共得到5种词语并将其作为图网络的节点表示,从而更有效地建模图神经网络的节点表征;同时,引入深度异构图卷积网络(HDGCN)进行偏好学习,它的深度策略和多层注意力机制可以让两种模型更加专注于自身需要的偏好感知并减少冗余信息.实验结果表明,在公开数据集Weibo和Twitter上,与当前主流的基于内容的单一模型LDAVAE相比,改进后的框架F1值分别提高了 2.8％和1.9％;与基于事实的单一模型GET相比,F1值分别提高了 2.1％和1.8％;同时,在LDAVAE+GET联合检测的情况下,比Pref-FEND的F1值分别提高了 1.1％和1.3％.实验结果验证了所改进模型的有效性.
Abstract
There are many methods for detecting fake news.The single method typically focuses only on information such as news content,social context,or external facts.On the other hand,joint detection methods integrate multiple modalities of information to achieve the detection goal.Pref-FEND is an example of a joint detection method that integrates news content and external facts.It extracts three types of word representations from news content and external facts,and uses dynamic graph convolutional net-works to capture relationships between word nodes.However,there are still shortcomings in how to make each modality more fo-cused on its preferred aspect.Therefore,the Pref-FEND model has been improved by using semantic mining to expand style words in news and entity linking to expand entity words in news.This results in five types of word as node representations in the graph neural network,enabling a more effective modeling of the node representation of the graph neural network.Additionally,a deep heterogeneous graph convolutional network(HDGCN)is introduced for preference learning.Its deep strategy and multi-layer attention mechanism allow both models to focus more on their own preferred perception and reduce redundant information.Experimental results demonstrate the effectiveness of the improved framework.On the public datasets Weibo and Twitter,com-pared to the current state-of-the-art content-based single model LDAVAE,the improved framework achieves an F1 score im-provement of 2.8％and 1.9％respectively.Compared to the fact-based single model GET,the F1 score improvement is 2.1％and 1.8％respectively.In the case of joint detection using LDAVAE+GET,the F1 score is 1.1％and 1.3％higher than Pref-FEND respectively.Experimental results validate the effectiveness of the improved model.
关键词
虚假新闻/图卷积网络/实体抽取/注意力机制/自然语言处理Key words
Fake news/Graph convolutional networks/Entity extraction/Attention mechanism/Natural language processing引用本文复制引用
出版年
2024
NETL
NSTL
万方数据