Detecting incongruent news headlines with auxiliary textual information
作者：
Highlights：
• We proposed a model with an attention mechanism for predicting incongruent headlines.
• We generated incongruent headline dataset from a real-world news.
• We found subtitle and image caption achieves better predictions.
• We further investigated the impact of the components in our proposed model.
• Our results reveals the possibility of real-world applications.
摘要
•We proposed a model with an attention mechanism for predicting incongruent headlines.•We generated incongruent headline dataset from a real-world news.•We found subtitle and image caption achieves better predictions.•We further investigated the impact of the components in our proposed model.•Our results reveals the possibility of real-world applications.
论文关键词：Fake news,Incongruent headline,Dataset generation,Deep learning,Hierarchical attention network
论文评审过程：Received 25 May 2021, Revised 21 January 2022, Accepted 8 March 2022, Available online 19 March 2022, Version of Record 29 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116866
