Preventing rumor spread with deep learning
作者：
Highlights：
• Using only a claim sentence of a rumor to identify false rumor.
• The proposed model can be used for fact-checking at an early stage.
• The model is evaluated with the rumors collected from Snopes and Politifact.
• Transfer learning is adopted to address the lack of rumor claims in a category.
• The model trained by the rumos in general topics is useful to be transferred.
摘要
•Using only a claim sentence of a rumor to identify false rumor.•The proposed model can be used for fact-checking at an early stage.•The model is evaluated with the rumors collected from Snopes and Politifact.•Transfer learning is adopted to address the lack of rumor claims in a category.•The model trained by the rumos in general topics is useful to be transferred.
论文关键词：Deep learning,Fact-checking,Rumor detection,Transfer learning
论文评审过程：Received 15 April 2021, Revised 31 December 2021, Accepted 16 February 2022, Available online 26 February 2022, Version of Record 2 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116688
