A Lexicon-Enhanced Attention Network for Aspect-Level Sentiment Analysis
Zhiying Ren, Guangping Zeng, Liu Chen, Qingchuan Zhang, Chunguang Zhang, Dingqi Pan
Abstract
Aspect-level sentiment classification is a fine-grained task in sentiment analysis. In recent years, researchers have realized the importance of the relationship between aspect term and sentence and many classification models based on deep learning network have been proposed. However, these end-to-end deep neural network models lack flexibility and do not consider the sentiment word information in existing methods. Therefore, we propose a lexicon-enhanced attention network (LEAN) based on bidirectional LSTM. LEAN not only can catch the sentiment words in a sentence but also concentrate on specific aspect information in a sentence. Moreover, leveraging lexicon information will enhance the model's flexibility and robustness. We experiment on the SemEval 2014 dataset and results find that our model achieves state-of-the-art performance on aspect-level sentiment classification.