Behind the cues: A benchmarking study for fake news detection

作者：

Highlights：

• Ensemble Machine learning for fake news detection.

• Optimal feature selection by linguistic cues enhanced with word embeddings.

• 95% accuracy in fake news detection.

• Experimentation under various fake news datasets.

• Introduce an unbiased dataset which includes multi-topic, multi-author articles.

摘要

•Ensemble Machine learning for fake news detection.•Optimal feature selection by linguistic cues enhanced with word embeddings.•95% accuracy in fake news detection.•Experimentation under various fake news datasets.•Introduce an unbiased dataset which includes multi-topic, multi-author articles.

论文关键词：Fake news,Linguistic analysis,Text classification,Machine learning,Ensemble machine learning

论文评审过程：Received 24 October 2018, Revised 20 March 2019, Accepted 20 March 2019, Available online 21 March 2019, Version of Record 1 April 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.03.036