Dynamic graph convolutional networks with attention mechanism for rumor detection on social media
| Autor: | Chong-kwon Kim, Younhyuk Choi, Hyungho Byun, Jiho Choi, Taewook Ko |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Theoretical computer science
Computer science Social Sciences Trees Task (project management) Machine Learning Sociology Psychology Human Activities Attention Disinformation Recurrent Neural Networks Sequence Multidisciplinary Communication Social Communication Eukaryota Plants Graph Social Networks Social Systems Medicine Network Analysis Research Article Computer and Information Sciences Neural Networks Science Artificial Intelligence TheoryofComputation_ANALYSISOFALGORITHMSANDPROBLEMCOMPLEXITY Humans Social media Information Dissemination business.industry Deep learning Cognitive Psychology Organisms Biology and Life Sciences Recognition Psychology Models Theoretical Rumor Communications Cognitive Science Neural Networks Computer Artificial intelligence business Social Media Feature learning Mechanism (sociology) Neuroscience |
| Zdroj: | PLoS ONE, Vol 16, Iss 8, p e0256039 (2021) PLoS ONE |
| ISSN: | 1932-6203 |
| DOI: | 10.1371/journal.pone.0256039 |
| Popis: | Social media has become an ideal platform for the propagation of rumors, fake news, and misinformation. Rumors on social media not only mislead online users but also affect the real world immensely. Thus, detecting the rumors and preventing their spread became an essential task. Some of the recent deep learning-based rumor detection methods, such as Bi-Directional Graph Convolutional Networks (Bi-GCN), represent rumor using the completed stage of the rumor diffusion and try to learn the structural information from it. However, these methods are limited to represent rumor propagation as a static graph, which isn’t optimal for capturing the dynamic information of the rumors. In this study, we propose novel graph convolutional networks with attention mechanisms, namedDynamic GCN, for rumor detection. We first represent rumor posts with their responsive posts as dynamic graphs. The temporal information is used to generate a sequence of graph snapshots. The representation learning on graph snapshots with attention mechanism captures both structural and temporal information of rumor spreads. The conducted experiments on three real-world datasets demonstrate the superiority of Dynamic GCN over the state-of-the-art methods in the rumor detection task. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|