Assessing dynamic qualities of investor sentiments for stock recommendation
作者：
Highlights：
• A novel method called CBRDQ is proposed to measure the qualities of investor sentiments about a specific stock.
• Different quality assessment methods are compared in a unifying stock recommendation framework.
• The proposed method is more appropriate for deriving sensible investment decisions than baselines.
• The effectiveness of CBRDQ confirms the variation of investors’ expertise in different stocks.
• Findings in this study have implications for trading practice and judgment of the quality of a review.
摘要
•A novel method called CBRDQ is proposed to measure the qualities of investor sentiments about a specific stock.•Different quality assessment methods are compared in a unifying stock recommendation framework.•The proposed method is more appropriate for deriving sensible investment decisions than baselines.•The effectiveness of CBRDQ confirms the variation of investors’ expertise in different stocks.•Findings in this study have implications for trading practice and judgment of the quality of a review.
论文关键词：Investment recommendation,Sentiment qualities,Investor-based social network
论文评审过程：Received 1 August 2020, Revised 4 November 2020, Accepted 25 November 2020, Available online 11 December 2020, Version of Record 11 December 2020.
论文官网地址：https://doi.org/10.1016/j.ipm.2020.102452
