Bidirectional-GRU Based on Attention Mechanism for Aspect-level Sentiment Analysis
Zhai Penghua, Zhang Dingyi · 2019
Aspect-level sentiment analysis is a fine-grained natural language processing task. For traditional deep learning models, they cannot accurately construct the aspect-level sentiment features. Such as, for the sentence of "the movie is very funny, but the seats in the theater is uncomfortable." For the movie, the polarity is positive, but it is negative for seats. To deal with this problem, we propose a bidirectional gated recurrent units neural network model that integrates the attention mechanism to solve the task of aspect-level sentiment analysis. The attention mechanism can focus on the different parts of a sentence when the sentence has several different aspects. Because we use a bidirectional gated recurrent unit, we can get independent context semantic information and get the deeper aspect sentiment information from the front and back, so that we can deal with the specific aspect sentiment polarity. Finally, we experiment on SemEval-2014 dataset and twitter dataset, the result of experiments verified the effectiveness of attention-based bidirectional gated recurrent unit on the aspect sentiment analysis. The model achieves good performance at different datasets and has further improvement comparing to previous models.