Aspect-level Sentiment Classification Based on Interactive Attention and Graph Convolutional Network

Abstract

Aspect-level sentiment analysis is a key task in fine-grained sentiment analysis,which aims to predict the sentiment tendency of different aspect terms in a sentence.In view of the fact that the current research combined with graph convolution network ignores the meaning of aspect terms themselves and the interaction between aspect terms and context,an interactive attention graph convolutional network model is proposed,named interactive attention graph convolution network(IAGCN).It firstlycombines BiLSTM and modified dynamic weights to model context.Secondly,the syntactic information is encoded by exploiting graph convolutional network on syntactic dependency tree.Then,the attention among context and aspect terms is investigated through interactive attention mechanism and the representation of context and aspect term is reconstructed.Finally,the sentiment polarity of a given aspect term is obtained through a softmax layer.Compared with the baseline models,the accuracy rate and F1 score of the proposed model improves by 0.56%~1.75% and 1.34%~4.04% on 5 datasets,respectively.At the same time,the pre-training model BERT is applied to this task.Compared with the IAGCN based on GloVe model,its accuracy rate and F1 score increases by 1.47%~3.95% and 2.59%~7.55%,respectively.Thus,the model effect has been further improved.

Keywords

• aspect-level sentiment analysis|deep learning|graph convolutional network|interactive attention mechanism|bert