SGDM-GRU: Spectral Graph Deep Learning Based Gated Recurrent Unit Model for Accurate Fake News Detection
Article
Article Title | SGDM-GRU: Spectral Graph Deep Learning Based Gated Recurrent Unit Model for Accurate Fake News Detection |
---|---|
ERA Journal ID | 17852 |
Article Category | Article |
Authors | Sahi, Aqeel, Albdair, Mostfa, Diykh, Mohammed, Abdulla, Shahab, Alghayab, Hadi, Aljebur, Kaled and Alkhafaji, Sarmad K.D. |
Journal Title | Expert Systems with Applications |
Journal Citation | 281 |
Article Number | 127572 |
Number of Pages | 12 |
Year | 2025 |
Publisher | Elsevier |
Place of Publication | United Kingdom |
ISSN | 0957-4174 |
1873-6793 | |
Digital Object Identifier (DOI) | https://doi.org/10.1016/j.eswa.2025.127572 |
Web Address (URL) | https://www.sciencedirect.com/science/article/pii/S0957417425011947 |
Abstract | With the surge of diverse news content on social media platforms, the necessity to effectively identify and combat fake news has never been more critical. The spreading of fake information in society could damage and harm the reliability of information as well as mislead public perception. As a result, several machine-learning-based models have been designed as promising methods to detect fake news. However, existing models experience some difficulties in capturing dynamic and historical social graph characteristics. This study proposes a novel approach called the SGDM-GRU (Spectral Graph Deep Learning Model based on Gated Recurrent Unit) to identify fake news. The proposed SGDM-GRU model incorporates GRU and represents network news patterns as graphs. We conducted several simulations on four datasets. Results showed that the SGDM-GRU model performs better than recently published fake news detection models. The proposed model obtained 97%, 98%, and 98% accuracy with Weibo, Twitter, Politifact, and Cossipcop datasets. With a combination of spectral graph deep learning models, the proposed model delivers a new finding in news detection research. |
Keywords | Fake news detection; SGDM; Graph; GRU |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 460207. Modelling and simulation |
Byline Affiliations | School of Mathematics, Physics and Computing |
Al-Shatrah University, Iraq | |
Al-Ayen University, Iraq | |
University of Misan, Iraq | |
University of Thi-Qar, Iraq | |
UniSQ College | |
TAFE Queensland | |
Al-Taff University, Iraq |
https://research.usq.edu.au/item/zx0y7/sgdm-gru-spectral-graph-deep-learning-based-gated-recurrent-unit-model-for-accurate-fake-news-detection
Download files
7
total views3
total downloads7
views this month3
downloads this month