Credibility assessment of financial stock tweets

作者：

Highlights：

• Machine learning classifiers can assess the credibility of financial stock tweets.

• Classifiers trained with novel financial features result in improved performance.

• Random Forest classifier outperforms other classifiers but depend on more features.

摘要

•Machine learning classifiers can assess the credibility of financial stock tweets.•Classifiers trained with novel financial features result in improved performance.•Random Forest classifier outperforms other classifiers but depend on more features.

论文关键词：Machine learning,Supervised learning,Twitter,Financial stock market,Feature selection

论文评审过程：Received 16 March 2020, Revised 28 August 2020, Accepted 17 November 2020, Available online 20 November 2020, Version of Record 14 December 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.114351