Feature-enhanced attention network for target-dependent sentiment classification

• Published in: Neurocomputing (Amsterdam) Vol. 307; pp. 91 - 97
• Main Authors: Yang, Min, Qu, Qiang, Chen, Xiaojun, Guo, Chaoxue, Shen, Ying, Lei, Kai
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 13.09.2018
• Subjects: Feature-enhanced sentiment analysis; Multi-view co-attention network; Target-dependent sentiment analysis; Target-dependent sentiment analysis; Multi-view co-attention network; Feature-enhanced sentiment analysis
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2018.04.042

In this paper, we propose a Feature-enhanced Attention Network to improve the performance of target-dependent Sentiment classification (FANS). Specifically, we first learn the feature-enhanced word representations by leveraging the unigram features, part of speech features and word position features. Second, we develop an multi-view co-attention network to learn a better multi-view sentiment-aware and target-specific sentence representation via interactively modeling the context words, target words and sentiment words. We conduct experiments to verify the effectiveness of our model on two real-world datasets in both English and Chinese. The experimental results demonstrate that FANS has robust superiority over competitors and sets state-of-the-art.