Propagation2Vec: Embedding partial propagation networks for explainable fake news early detection
作者：
Highlights：
• The propagation pattern of news on social media can facilitate fake news detection.
• Propagation2Vec emphasises informative nodes/cascades to detect fake news.
• Propagation2Vec early reconstructs complete propagation networks by partial networks.
• Propagation2Vec achieves state-of-the-art performance for fake news early detection.
• The underlying logic of Propagation2Vec is explainable by the attention weights.
摘要
•The propagation pattern of news on social media can facilitate fake news detection.•Propagation2Vec emphasises informative nodes/cascades to detect fake news.•Propagation2Vec early reconstructs complete propagation networks by partial networks.•Propagation2Vec achieves state-of-the-art performance for fake news early detection.•The underlying logic of Propagation2Vec is explainable by the attention weights.
论文关键词：Fake news detection,News propagation networks,Detection deadline,Network embedding learning
论文评审过程：Received 20 January 2021, Revised 22 April 2021, Accepted 30 April 2021, Available online 11 May 2021, Version of Record 11 May 2021.
论文官网地址：https://doi.org/10.1016/j.ipm.2021.102618
