Investment strategies applied to the Brazilian stock market: A methodology based on Sentiment Analysis with deep learning

作者：

Highlights：

• Sentiment Analysis of news was the basis of stock market investment strategies.

• The focus was on news in Portuguese and on the Brazilian stock market.

• Different Artificial Neural Networks for Sentiment Analysis were evaluated.

• An influence of the predominant daily sentiment in the stock market was observed.

• Investment strategies led to higher profits when compared to classic ones.

摘要

•Sentiment Analysis of news was the basis of stock market investment strategies.•The focus was on news in Portuguese and on the Brazilian stock market.•Different Artificial Neural Networks for Sentiment Analysis were evaluated.•An influence of the predominant daily sentiment in the stock market was observed.•Investment strategies led to higher profits when compared to classic ones.

论文关键词：Sentiment Analysis,Artificial Neural Networks,MLP,LSTM,CNN,Stock Market

论文评审过程：Received 28 September 2020, Revised 27 April 2021, Accepted 21 June 2021, Available online 26 June 2021, Version of Record 2 July 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.115470