GCNDA: Graph Convolutional Networks with Dual Attention Mechanisms for Aspect Based Sentiment Analysis

Abstract

As the amount of user-generated content on the web continues to increase, a great interest has been shown in aspect-level sentiment analysis, which provides more detailed information than general sentiment analysis. In recent years, neural-based models have achieved success in this task because of their powerful representation learning capabilities. However, they ignore that the sentiment polarity of the target is related to the entire text structure. In this paper, we present a method based on graph convolutional neural networks named GCNDA, in which the given text is considered as a graph and the target is the specific region of the graph. Dual graph-based attention models are used to concentrate on the relation between words and certain regions of the graph. We conduct comprehensive experiments on publicly accessible datasets, and results demonstrate that our model outperforms the state-of-the-art baselines.