Deep contextualized text representation and learning for fake news detection

作者：

Highlights：

• Using different deep contextualized text representation models for fake news detection.

• Providing a comprehensive comparative study on text representation for fake news detection.

• Proposing different neural classifiers for word and text level representation.

• Using Gaussian noise to overcome the overfitting problem.

• Outperforming state-of-the-art methods in the field.

摘要

•Using different deep contextualized text representation models for fake news detection.•Providing a comprehensive comparative study on text representation for fake news detection.•Proposing different neural classifiers for word and text level representation.•Using Gaussian noise to overcome the overfitting problem.•Outperforming state-of-the-art methods in the field.

论文关键词：Fake news detection,Deep neural network,Contextualized text representation

论文评审过程：Received 29 October 2020, Revised 13 July 2021, Accepted 7 August 2021, Available online 8 September 2021, Version of Record 8 September 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102723