Automatic construction of target-specific sentiment lexicon
作者：
Highlights：
• An approach to construct a target-specific sentiment lexicon is proposed.
• An unsupervised method to extract opinion targets is proposed.
• The method achieves both high accuracy and recall in extraction.
• A framework is proposed to classify sentiment polarities of opinion pairs accurately.
• The framework extracts and integrates different sources of sentiment information.
摘要
•An approach to construct a target-specific sentiment lexicon is proposed.•An unsupervised method to extract opinion targets is proposed.•The method achieves both high accuracy and recall in extraction.•A framework is proposed to classify sentiment polarities of opinion pairs accurately.•The framework extracts and integrates different sources of sentiment information.
论文关键词：Opinion mining,Sentiment lexicon,Sentiment analysis,Opinion target extraction
论文评审过程：Received 14 June 2018, Revised 21 August 2018, Accepted 10 September 2018, Available online 13 September 2018, Version of Record 21 September 2018.
论文官网地址：https://doi.org/10.1016/j.eswa.2018.09.024
