Aspect-based sentiment analysis using adaptive aspect-based lexicons

作者：

Highlights：

• A combination of dynamic and static lexicons outperforms isolated use of each type.

• In lexicon generation using GA, frequent terms tend to have the most robust scores.

• PoS-based filtering of terms enhances the quality of dynamic lexicon generation.

• Removal of stop words elevates the quality of the dynamic lexicons generation.

摘要

•A combination of dynamic and static lexicons outperforms isolated use of each type.•In lexicon generation using GA, frequent terms tend to have the most robust scores.•PoS-based filtering of terms enhances the quality of dynamic lexicon generation.•Removal of stop words elevates the quality of the dynamic lexicons generation.

论文关键词：Aspect-based,Sentiment analysis,Opinion mining,Lexicon generation,Genetic algorithm

论文评审过程：Received 5 May 2019, Revised 22 December 2019, Accepted 22 January 2020, Available online 23 January 2020, Version of Record 31 January 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2020.113234