ALDONAr: A hybrid solution for sentence-level aspect-based sentiment analysis using a lexicalized domain ontology and a regularized neural attention model
作者:
Highlights:
• We present a hybrid model for aspect-based sentiment analysis.
• The domain information is captured by a sentiment domain ontology.
• The neural model is based on context attention and a classification module.
• Using standard datasets we show that the new model outperforms existing models.
摘要
•We present a hybrid model for aspect-based sentiment analysis.•The domain information is captured by a sentiment domain ontology.•The neural model is based on context attention and a classification module.•Using standard datasets we show that the new model outperforms existing models.
论文关键词:Aspect-based sentiment analysis,Hybrid model,Lexicalized domain ontology,Bidirectional gated neural network,Regularization
论文评审过程:Received 13 September 2019, Revised 20 December 2019, Accepted 20 January 2020, Available online 31 January 2020, Version of Record 31 January 2020.
论文官网地址:https://doi.org/10.1016/j.ipm.2020.102211