Sector-level sentiment analysis with deep learning

作者：

Highlights：

• The paper presents Natural Language Processing (NLP) methods for financial news analysis.

• The proposed semi-supervised approach achieved competitive results in sentiment analysis.

• New research towards sector prediction with several applications in stock market analysis.

• The proposed sector prediction model achieved high predictive performance across all sectors.

• A hybrid system for sector-level sentiment analysis that combines sector and sentiment models.

摘要

•The paper presents Natural Language Processing (NLP) methods for financial news analysis.•The proposed semi-supervised approach achieved competitive results in sentiment analysis.•New research towards sector prediction with several applications in stock market analysis.•The proposed sector prediction model achieved high predictive performance across all sectors.•A hybrid system for sector-level sentiment analysis that combines sector and sentiment models.

论文关键词：Natural language processing,Machine learning,Financial sentiment analysis

论文评审过程：Received 27 July 2021, Revised 24 September 2022, Accepted 25 September 2022, Available online 1 October 2022, Version of Record 20 October 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.109954