Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection

  title={Towards Propagation Uncertainty: Edge-enhanced Bayesian Graph Convolutional Networks for Rumor Detection},
  author={Lingwei Wei and Dou Hu and Wei Zhou and Zhaojuan Yue and Songlin Hu},
Detecting rumors on social media is a very critical task with significant implications to the economy, public health, etc. Previous works generally capture effective features from texts and the propagation structure. However, the uncertainty caused by unreliable relations in the propagation structure is common and inevitable due to wily rumor producers and the limited collection of spread data. Most approaches neglect it and may seriously limit the learning of features. Towards this issue, this… 

Figures and Tables from this paper

Region-enhanced Deep Graph Convolutional Networks for Rumor Detection
A novel region-enhanced deep graph convolutional network (RDGCN) that enhances the propagation features of rumors by learning regionalized propagation patterns and trains to learn the propagation patterns by unsupervised learning is proposed.
Rumor Detection with Self-supervised Learning on Texts and Social Graph
This work explores contrastive self-supervised learning on heterogeneous information sources, so as to reveal their relations and characterize rumors better, and develops a framework for automatic rumor detection on social media.
Towards Fine-Grained Reasoning for Fake News Detection
A fine-grained reasoning framework is proposed by following the human’s information-processing model, a mutual-reinforcement-based method for incorporating human knowledge about which evidence is more important is introduced, and a prior-aware bi-channel kernel graph network is designed to model subtle differences between pieces of evidence.
PALI-NLP at SemEval-2022 Task 4: Discriminative Fine-tuning of Transformers for Patronizing and Condescending Language Detection
A novel Transformer-based model and its ensembles are proposed to accurately understand such language context for PCL detection and two fine-tuning strategies are applied to facilitate comprehension of the subtle and subjective nature of PCL.


Jointly Embedding the Local and Global Relations of Heterogeneous Graph for Rumor Detection
A novel global-local attention network (GLAN) for rumor detection is presented, which jointly encodes the local semantic and global structural information in the message propagation graph.
Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks
A novel bi-directional graph model is proposed, named Bi-Directional Graph Convolutional Networks (Bi-GCN), to explore both characteristics of rumors by operating on both top-down and bottom-up propagation of rumors.
Call Attention to Rumors: Deep Attention Based Recurrent Neural Networks for Early Rumor Detection
A deep attention model based on recurrent neural networks to selectively learn temporal representations of sequential posts for rumor identification that outperforms state-of-the-art baselines by detecting rumors more quickly and accurately than competitors.
Reply-Aided Detection of Misinformation via Bayesian Deep Learning
This work proposes a Bayesian deep learning model that outperforms the state-of-the-art detection models of misinformation detection and develops a Stochastic Gradient Variational Bayes algorithm to approximate the analytically intractable posterior distribution.
Detect Rumors in Microblog Posts Using Propagation Structure via Kernel Learning
A kernel-based method is proposed, which captures high-order patterns differentiating different types of rumors by evaluating the similarities between their propagation tree structures, and can detect rumors more quickly and accurately than state-of-the-art rumor detection models.
FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
This work proposes Factual News Graph, a novel graphical social context representation and learning framework for fake news detection that is scalable in training as it does not have to maintain all nodes, and it is efficient at inference time, without the need to re-process the entire graph.
GCAN: Graph-aware Co-Attention Networks for Explainable Fake News Detection on Social Media
This paper solves the fake news detection problem under a more realistic scenario on social media by developing a novel neural network-based model, Graph-aware Co-Attention Networks (GCAN), which can significantly outperform state-of-the-art methods by 16% in accuracy on average.
False rumors detection on Sina Weibo by propagation structures
A graph-kernel based hybrid SVM classifier which captures the high-order propagation patterns in addition to semantic features such as topics and sentiments and is 88% confident in detecting an average false rumor just 24 hours after the initial broadcast.
Modeling Conversation Structure and Temporal Dynamics for Jointly Predicting Rumor Stance and Veracity
Experimental results on two benchmark datasets show that the proposed hierarchical multi-task learning framework for jointly predicting rumor stance and veracity on Twitter outperforms previous methods in both rumor stance classification andVeracity prediction.
Rumor Detection on Twitter with Tree-structured Recursive Neural Networks
This work proposes two recursive neural models based on a bottom-up and a top-down tree-structured neural networks for rumor representation learning and classification, which naturally conform to the propagation layout of tweets.