Investment recommendation by discovering high-quality opinions in investor based social networks

作者：

Highlights：

• Qualities of investor opinions can be predicted by multiple factors.

• Low-quality opinions will influence the effectiveness of sentiment aggregation.

• Opinions posted on the Stocktwits platform are useful for stock recommendation.

• Stock recommendation can be improved with predicted qualities of investor opinions.

摘要

•Qualities of investor opinions can be predicted by multiple factors.•Low-quality opinions will influence the effectiveness of sentiment aggregation.•Opinions posted on the Stocktwits platform are useful for stock recommendation.•Stock recommendation can be improved with predicted qualities of investor opinions.

论文关键词：Investment recommendation,Investor based social network,Data mining

论文评审过程：Received 15 April 2017, Revised 15 February 2018, Accepted 24 February 2018, Available online 24 February 2018, Version of Record 13 September 2018.

论文官网地址：https://doi.org/10.1016/j.is.2018.02.011