Detection of temporality at discourse level on financial news by combining Natural Language Processing and Machine Learning

作者：

Highlights：

• Detection of temporality in financial news using NLP and Machine Learning techniques.

• Three linguistic analysis: dependency, proximity and discourse.

• Combination of textual, numerical and temporal features.

• Promising results regarding temporal knowledge extraction for predictive analysis.

• Strong potential for decision making in financial markets.

摘要

•Detection of temporality in financial news using NLP and Machine Learning techniques.•Three linguistic analysis: dependency, proximity and discourse.•Combination of textual, numerical and temporal features.•Promising results regarding temporal knowledge extraction for predictive analysis.•Strong potential for decision making in financial markets.

论文关键词：Computational Linguistics,Financial news,Knowledge extraction,Machine Learning,Natural Language Processing,Temporal analysis

论文评审过程：Received 23 November 2020, Revised 27 September 2021, Accepted 4 February 2022, Available online 24 February 2022, Version of Record 26 February 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116648