Attention-Enhanced Graph Convolutional Networks for Aspect-Based Sentiment Classification with Multi-Head Attention

Guangtao Xu,Peiyu Liu,Jie Liu,Fuyong Xu,Zhenfang Zhu

doi:10.3390/app11083640

Guangtao Xu, Peiyu Liu + Show 3 more

Open Access

https://doi.org/10.3390/app11083640

Copy DOI

Abstract

The purpose of aspect-based sentiment classification is to identify the sentiment polarity of each aspect in a sentence. Recently, due to the introduction of Graph Convolutional Networks (GCN), more and more studies have used sentence structure information to establish the connection between aspects and opinion words. However, the accuracy of these methods is limited by noise information and dependency tree parsing performance. To solve this problem, we proposed an attention-enhanced graph convolutional network (AEGCN) for aspect-based sentiment classification with multi-head attention (MHA). Our proposed method can better combine semantic and syntactic information by introducing MHA and GCN. We also added an attention mechanism to GCN to enhance its performance. In order to verify the effectiveness of our proposed method, we conducted a lot of experiments on five benchmark datasets. The experimental results show that our proposed method can make more reasonable use of semantic and syntactic information, and further improve the performance of GCN.

Highlights

To solve the above two problems, we proposed an attention-enhanced graph convolutional network for aspect-based sentiment classification with multi-head attention
We introduced multi-head self-attention to capture contextual semantic information, used multi-head interactive attention to interact semantic and syntactic information to obtain a more complete feature representation
This result reflects the superiority of graph convolutional network in Aspect-based sentiment classification (ABSC) task

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Aspect-based sentiment classification (ABSC) [1] is a fine-grained subtask in the field of sentiment analysis. Its purpose is to identify the sentiment polarity of the aspects that clearly appear in the sentence. In a restaurant review: “This restaurant has a good environment, but the price is a bit expensive”, the sentiment polarity of the two aspects “environment” and “price” are positive and negative, respectively. Aspects are usually noun or noun phrases. The difficulty of aspect-based sentiment classification task is how to accurately find out the opinion words related to aspects. In the above example, the opinion words corresponding to environment and price are “good” and “expensive”, respectively

Objectives

Methods

Results

Conclusion