ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2021, Vol. 58 ›› Issue (7): 1395-1411.doi: 10.7544/issn1000-1239.2021.20200810

所属专题: 2021虚假信息检测专题

• 信息处理 • 上一篇    下一篇



  1. 1(华北计算机系统工程研究所 北京 100083);2(中国科学院信息工程研究所 北京 100093);3(中国科学院大学网络空间安全学院 北京 100049) (
  • 出版日期: 2021-07-01
  • 基金资助: 

A Rumor Detection Approach Based on Multi-Relational Propagation Tree

Hu Dou1, Wei Lingwei2,3, Zhou Wei2, Huai Xiaoyong1, Han Jizhong2, Hu Songlin2,3   

  1. 1(National Computer System Engineering Research Institute of China, Beijing 100083);2(Institute of Information Engineering, Chinese Academy of Sciences, Beijing 100093);3(School of Cyber Security, University of Chinese Academy of Sciences, Beijing 100049)
  • Online: 2021-07-01
  • Supported by: 
    This work was supported by the National Key Research and Development Program of China (2018YFC0806900).

摘要: 近年来,社交媒体为人们消费信息提供便利的同时,也逐渐成为谣言产生和传播的温床.为了降低谣言的危害性,谣言检测受到研究学者的广泛关注.近期研究主要基于博文内容和传播结构信息,利用深度学习模型进行谣言检测.但是,这些方法仅考虑传播过程中博文之间的显式交互关系,忽略了对潜在关系的建模,难以捕捉到丰富的传播结构特征.例如,在转发(或评论)的交互形式下,多个转发者(或评论者)之间往往也存在局部的隐式交互.针对该挑战,提出一种基于多关系传播树的谣言检测方法,建模博文之间的多种依赖关系,同时增强重要博文的影响力,以捕获更丰富的信息传播结构特征.具体地,基于文本内容和传播树结构建立异构图,使用多关系图卷积网络建模父子节点之间的层间依赖关系和兄弟节点之间的层内依赖关系,并利用源节点和关键传播节点建模重要博文在信息传播中的潜在影响力,从而学习一个更全面的特征向量表示,用于检测谣言.在3个公开的真实数据集上进行广泛的实验,结果表明该方法具有比其他基线方法更高的谣言检测性能.

关键词: 谣言检测, 传播树, 图卷积网络, 信息传播, 社交媒体

Abstract: Rumor detection has aroused increasing attention due to the damage caused by rampant rumors. Recent studies leverage the post content and propagation structure to detect rumors based on deep-learning based models. However, most of them focus on explicit interactions between posts in the spreading process, while ignoring the modeling of implicit relations, which limits the ability to encode the propagation structure. For example, in the interactive pattern of forwarding (commenting), there are often local implicit interactions between multiple forwarded (commented) posts. In this paper, we propose a rumor detection approach based on a multi-relational propagation tree, investigating multiple kinds of dependencies between posts and enhancing the influence of important posts, to capture richer propagation patterns. Specifically, we formulate the textual content and the propagation tree structure as a heterogeneous graph. Then, we present a novel multi-relational graph convolutional network to learn the inter-level dependency between parent and child nodes and the intra-level dependency between sibling nodes. Meanwhile, we exploit the source post and key spreading posts to model the potential influence of important posts in the spreading process. Finally, we aggregate the node features to learn a more discriminative representation for rumor detection. Extensive experiments on three public benchmark datasets demonstrate the effectiveness and superiority of our proposed method.

Key words: rumor detection, propagation tree, graph convolutional network, information propagation, social media