Care more about customers: Unsupervised domain-independent aspect detection for sentiment analysis of customer reviews

作者：

Highlights：

• We proposed a model used for detecting explicit and implicit aspects in sentiment analysis.

• The model performs the detection with finding single and multi-word aspects, filtering by A-score metric and pruning.

• Experimental results show considerable improvements of the proposed model over conventional techniques.

摘要

•We proposed a model used for detecting explicit and implicit aspects in sentiment analysis.•The model performs the detection with finding single and multi-word aspects, filtering by A-score metric and pruning.•Experimental results show considerable improvements of the proposed model over conventional techniques.

论文关键词：Aspect detection,Opinion mining,Review mining,Sentiment analysis,Implicit aspect

论文评审过程：Received 8 January 2013, Revised 21 July 2013, Accepted 2 August 2013, Available online 13 August 2013.

论文官网地址：https://doi.org/10.1016/j.knosys.2013.08.011