Graph Convolutional Network with Two Types of Weight Mechanisms for Aspect-Based Sentiment Analysis

In this paper, we propose an approach to leverage inter aspects relation and Rely Graph Convolutional Networks (RelyGCN) for aspect sentiment analysis. More specifically, an ordinary dependency graph is first constructed for each sentence over the dependency tree. Then we extract aspects by L-Layer GCNs and construct their relation. Finally, we will predict the sentiment polarity (negative, neutral and positive) of the sentence S towards the aspect A by the feature fusing layer and the output layer.