A dual framework for implicit and explicit emotion recognition: An ensemble of language models and computational linguistics

作者：

Highlights：

• A novel insight is suggested to recognize emotion from text.

• Simultaneous discovery of explicit and implicit emotions reflects feeling accurately.

• A modified TF-IDF is proposed to weigh expressions in short texts.

• Combining emotional models, increases the accuracy of emotion recognition in texts.

摘要

•A novel insight is suggested to recognize emotion from text.•Simultaneous discovery of explicit and implicit emotions reflects feeling accurately.•A modified TF-IDF is proposed to weigh expressions in short texts.•Combining emotional models, increases the accuracy of emotion recognition in texts.

论文关键词：Sentiment analysis (SA),Opinion mining,Explicit emotion recognition (EER),Implicit emotion recognition (IER),Language model (LM),Feature weighing,Dual framework,Ensemble method, Computational linguistics,Machine learning

论文评审过程：Received 15 July 2021, Revised 29 October 2021, Accepted 15 February 2022, Available online 4 March 2022, Version of Record 15 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116686