Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks

Bian, Tian; Xiao, Xi; Xu, Tingyang; Zhao, Peilin; Huang, Wenbing; Rong, Yu; Huang, Junzhou

doi:10.48550/arxiv.2001.06362

Cited by 7 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Efficiency. In terms of efficiency, the following observations can be made from our experiments on both datasets: (1) compared with the normal training process, training with GEM and EWC requires slightly more time; (2) there is no significant difference in training time between GEM and EWC; and (3) the impact of the parameters, i.e., sample size and λ, on the training time is also not significant.…”

Section: Continual Learningmentioning

confidence: 73%

“…The idea of using propagation patterns to detect fake news has been explored in a number of previous studies [18,21,40,52,53,63], where different types of models have been considered: Wu et al [52] use a hybrid Support Vector Machine (SVM), Ma et al [21] use Propagation Tree Kernel; Wu et al [53] incorporate Long Short-Term Memory (LSTM) cells into the Recurrent Neural Network (RNN) model; Liu et al [18] use both RNNs and Convolutional Neural Networks (CNNs); Shu et al [40] and Zhou et al [63] propose different types of features and compare multiple commonly used machine learning models. The most relevant works include [2,20,24], which also apply GNNs to study propagation patterns. However, in addition to selecting a different GNN algorithm specifically designed for graph classification (refer to Section 2 for further explanation), our work mainly focuses on the following questions:…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Continual Learning for Fake News Detection from Social Media

Han

Karunasekera

Leckie

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Although significant effort has been applied to fact-checking, the prevalence of fake news over social media, which has profound impact on justice, public trust and our society as a whole, remains a serious problem. In this work, we focus on propagation-based fake news detection, as recent studies have demonstrated that fake news and real news spread differently online. Specifically, considering the capability of graph neural networks (GNNs) in dealing with non-Euclidean data, we use GNNs to differentiate between the propagation patterns of fake and real news on social media. In particular, we concentrate on two questions: (1) Without relying on any text information, e.g., tweet content, replies and user descriptions, how accurately can GNNs identify fake news? Machine learning models are known to be vulnerable to adversarial attacks, and avoiding the dependence on text-based features can make the model less susceptible to the manipulation of advanced fake news fabricators. (2) How to deal with new, unseen data? In other words, how does a GNN trained on a given dataset perform on a new and potentially vastly different dataset? If it achieves unsatisfactory performance, how do we solve the problem without re-training the model on the entire data from scratch, which would become prohibitively expensive in practice as the data volumes grow? We study the above questions on two datasets with thousands of labelled news items, and our results show that: (1) GNNs can achieve comparable or superior performance without any text information to state-of-the-art methods. (2) GNNs trained on a given dataset may perform poorly on new, unseen data, and direct incremental training cannot solve the problem-this issue has not been addressed in the previous work that applies GNNs for fake news detection. In order to solve the problem, we propose a method that achieves balanced performance on both existing and new datasets, by using techniques from continual learning to train GNNs incrementally. CCS CONCEPTS• Computing methodologies → Supervised learning by classification; Neural networks.

show abstract

Section: Continual Learningmentioning

confidence: 73%

Section: Introductionmentioning

confidence: 99%

Continual Learning for Fake News Detection from Social Media

Han

Karunasekera

Leckie

2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…• The title and the body text are concatenated to extract its textual content 𝑊 = {𝑤 0 , 𝑤 1 , ...}. • Co-reference resolution 4 is performed to replace all the mentions in 𝑊 that refer to the same real-world entity with a single token (Line 2). In the given example, "Kohli" is replaced by "Virat Kohli".…”

Section: Knowledge Graph Constructionmentioning

confidence: 99%

“…(3) For our knowledge-based model, the hyper-parameters for SubGNN are selected from the following ranges: batch size ∈ [64, 128], learning rate ∈ [3𝑒-5, 1𝑒-3], number of layers ∈ [1,4], number of structure anchor patches |𝐴 𝑆 | ∈ [15,45], and feed forward hidden dimension sizes ∈ [32,64] with dropout ∈ [0.0, 0.4]. (4) For our multi-modal approach, number of feed forward layers ∈ [2,4] with hidden dimension sizes ∈ [8,64] and dropout ∈ [0.0, 0.2]. ( 5) For the baseline of [24], the embedding dimensions of 𝐾𝐺 𝐹 and 𝐾𝐺 𝑇 are in the range of [30,50] for PolitiFact, and [50,100] for GossipCop.…”

Section: Baselinesmentioning

confidence: 99%

Knowledge Enhanced Multi-modal Fake News Detection

Han¹,

Silva²,

Luo³

et al. 2021

Preprint

View full text Add to dashboard Cite

Recent years have witnessed the significant damage caused by various types of fake news. Although considerable effort has been applied to address this issue and much progress has been made on detecting fake news, most existing approaches mainly rely on the textual content and/or social context, while knowledge-level information-entities extracted from the news content and the relations between them-is much less explored. Within the limited work on knowledge-based fake news detection, an external knowledge graph is often required, which may introduce additional problems: it is quite common for entities and relations, especially with respect to new concepts, to be missing in existing knowledge graphs, and both entity prediction and link prediction are open research questions themselves. Therefore, in this work, we investigate knowledge-based fake news detection that does not require any external knowledge graph. Specifically, our contributions include: (1) transforming the problem of detecting fake news into a subgraph classification task-entities and relations are extracted from each news item to form a single knowledge graph, where a news item is represented by a subgraph. Then a graph neural network (GNN) model is trained to classify each subgraph/news item.(2) Further improving the performance of this model through a simple but effective multi-modal technique that combines extracted knowledge, textual content and social context. Experiments on multiple datasets with thousands of labelled news items demonstrate that our knowledge-based algorithm outperforms existing counterpart methods, and its performance can be further boosted by the multi-modal approach. CCS CONCEPTS• Computing methodologies → Supervised learning by classification; Neural networks.

show abstract

“…Graph neural networks (GNNs), a family of neural models for learning latent node representations in a graph, have been widely used in different graph learning tasks and achieved remarkable success (Kipf & Welling, 2016;Ding, Li, Bhanushali, & Liu, 2019;Monti, Frasca, Eynard, Mannion, & Bronstein, 2019;Bian et al, 2020). Due to the superior modeling power, researchers have proposed to leverage GNNs for solving the disinformation detection problem.…”

Section: Advanced Graph Mining For Disinformation Detectionmentioning

confidence: 99%

Combating Disinformation in a Social Media Age

Shu

Bhattacharjee

Alatawi

et al. 2020

Preprint

View full text Add to dashboard Cite

The creation, dissemination, and consumption of disinformation and fabricated content on social media is a growing concern, especially with the ease of access to such sources, and the lack of awareness of the existence of such false information. In this paper, we present an overview of the techniques explored to date for the combating of disinformation with various forms. We introduce different forms of disinformation, discuss factors related to the spread of disinformation, elaborate on the inherent challenges in detecting disinformation, and show some approaches to mitigating disinformation via education, research, and collaboration. Looking ahead, we present some promising future research directions on disinformation.

show abstract

Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networks

Cited by 7 publications

References 19 publications

Continual Learning for Fake News Detection from Social Media

Continual Learning for Fake News Detection from Social Media

Knowledge Enhanced Multi-modal Fake News Detection

Combating Disinformation in a Social Media Age

Contact Info

Product

Resources

About