传播树结构结点及路径双注意力谣言检测模型  

Dual-attention Network Model on Propagation Tree Structures for Rumor Detection

作　　者：韩雪明 贾彩燕[1,2] 李轩涯 张鹏飞 HAN Xueming;JIA Caiyan;LI Xuanya;ZHANG Pengfei(School of Computer and Information Technology,Beijing Jiaotong University,Beijing 100044,China;Beijing Key Lab of Traffic Data Analysis and Mining,Beijing Jiaotong University,Beijing 100044,China;Baidu Online Network Technology(Beijing)Co.,Ltd.,Beijing 100085,China)

机构地区：[1]北京交通大学计算机与信息技术学院,北京100044 [2]北京交通大学交通数据分析与挖掘北京市重点实验室,北京100044 [3]百度在线网络技术(北京)有限公司,北京100085

出　　处：《计算机科学》2023年第4期22-31,共10页Computer Science

基　　金：国家重点研发计划(2017YFC1703506);国家自然科学基金(61876016);中央高校基本科研业务费专项资金(2019JBZll0);百度松果计划开放研究基金。

摘　　要：随着社交媒体平台的快速发展和移动设备的普及,人与人之间的交互变得更加便捷。但同时,谣言在社交媒体上也更加肆虐,给公众和社会安全带来巨大的隐患。在现实世界中,用户在发表自己的评论之前,往往会首先观测其他已经发表的帖子,尤其是即将评论的帖子上下文。现有的一些谣言检测方法虽然使用了谣言传播过程中的传播结构,基于群体智能原则提取用户间的相互质疑或事实线索,极大地提高了谣言检测的效果,但是对传播结构的深层非直接隐式关系及关键帖子和关键路径重要性的学习能力不足。据此,文中提出了一种基于传播树的结点及路径双注意力谣言检测模型DAN-Tree(Dual-attention Network Model on Propagation Tree Structures)。该模型使用Transformer结构学习传播路径中帖子间的隐式语义关系,并利用注意力机制学习路径中结点的重要度;其次,利用注意力机制对路径表示进行加权聚合得到整个传播树的表示向量;最后,基于传播树表示向量进行谣言分类。此外,我们使用结构嵌入方法学习帖子在传播树上的空间位置信息,进一步对谣言传播结构上的深层结构和语义信息进行融合。在4个经典数据集上的实验结果表明:DAN-Tree模型在其中的3个数据集上都超过了目前已有文献的最优结果。在Twitter15和Twitter16数据集上正确率指标分别提升了1.81%和2.39%,在PHEME数据集上F1指标提升了7.51%。With the rapid development of social media and the popularity of mobile devices,the interaction between users has become more convenient.But at the same time,rumors on social media are more and more rampant,which brings hidden dangers to the public and social safety.In the real world,users often express their own opinions after observing other microblogs that have been posted,especially the context of the microblog to be replied.Although some existing rumor detection methods learn the propagation patterns on propagation trees of rumors to extract clues of user interrogation or factual evidences based on the principle of crowd wisdom,which greatly improves the performance of rumor detection,they only focus on those microblogs that have direct response relationships,and Lack of ability to fully mine the indirect and implicit relationships among microblogs in the process of rumor propagation.Therefore,in this paper,a node and path dual-attention network on propagation tree structures(DAN-Tree)for debunking rumors is proposed.First,the model uses the Transformer structure to fully learn the implicit semantic relationship between posts in the propagation path,and then uses the attention mechanism to perform weighted fusion to obtain the feature vector of the propagation path.Secondly,the path representation is weighted and aggregated by using the attention mechanism to obtain the representation vector of the whole propagation tree.In addition,the structure embedding method is used to learn the spatial location information of the post on the propagation tree,which realizes the effective fusion of the deep structure and semantic information in the rumor propagation structure.The effect of the DAN-Tree model is verified on four classic datasets.Experimental results show that the DAN-Tree model surpasses the best results of the existing literature on the three datasets:the accuracy of the Twitter15 and Twitter16 datasets increases by 1.81%and 2.39%,respectively,and the F1 score of the PHEME dataset increases by 7.51%,whic

关 键 词：谣言检测 传播结构 注意力机制 社交媒体 深度学习 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]