Aspect-level sentiment analysis based on aspect-sentence graph convolution network

Wenqian Shang, Jiazhao Chai, Jianxiang Cao, Xia Lei, Haibin Zhu, Yongkai Fan, Weiping Ding

Abstract: Highlights•Proposing a method to calculate the adjacency matrix of the relational graph of aspect words and a method to calculate the adjacency matrix of a syntactic dependency graph.•Proposesing a multiple ASGCN model architectures, and designing an experiment to compare the sentiment classification performance of these architectures.•Experimental results show that the proposed model can percept the semantic relationships.