The role of idioms in sentiment analysis

作者：

Highlights：

• Idiom-based features significantly improve sentiment classification results.

• This study provides resources that can support further research into sentiment analysis.

• A comprehensive collection of 580 idioms annotated with sentiment polarity.

• A set of local grammars that can be used to recognize occurrences of these idioms.

• A corpus of 2521 annotated sentences in which idioms are used in context.

摘要

•Idiom-based features significantly improve sentiment classification results.•This study provides resources that can support further research into sentiment analysis.•A comprehensive collection of 580 idioms annotated with sentiment polarity.•A set of local grammars that can be used to recognize occurrences of these idioms.•A corpus of 2521 annotated sentences in which idioms are used in context.

论文关键词：Emotion recognition,Sentiment analysis,Natural language processing,User-generated content,Tagging

论文评审过程：Available online 28 May 2015, Version of Record 17 June 2015.

论文官网地址：https://doi.org/10.1016/j.eswa.2015.05.039