Transformer-Based Graph Convolutional Network for Sentiment Analysis

Applied Sciences

Oloulade Babatounde Moctard¹  Barakat AlBadani¹  Raeed Al-Sabri¹  Ronghua Shi¹  Jian Dong¹ 

[1] School of Computer Science and Engineering, Central South University, Changsha 410083, China;

关键词: sentiment analysis;    graph neural network;    deep learning;    NLP transformer;   

DOI  :  10.3390/app12031316

来源: DOAJ

【 摘 要 】

Sentiment Analysis is an essential research topic in the field of natural language processing (NLP) and has attracted the attention of many researchers in the last few years. Recently, deep neural network (DNN) models have been used for sentiment analysis tasks, achieving promising results. Although these models can analyze sequences of arbitrary length, utilizing them in the feature extraction layer of a DNN increases the dimensionality of the feature space. More recently, graph neural networks (GNNs) have achieved a promising performance in different NLP tasks. However, previous models cannot be transferred to a large corpus and neglect the heterogeneity of textual graphs. To overcome these difficulties, we propose a new Transformer-based graph convolutional network for heterogeneous graphs called Sentiment Transformer Graph Convolutional Network (ST-GCN). To the best of our knowledge, this is the first study to model the sentiment corpus as a heterogeneous graph and learn document and word embeddings using the proposed sentiment graph transformer neural network. In addition, our model offers an easy mechanism to fuse node positional information for graph datasets using Laplacian eigenvectors. Extensive experiments on four standard datasets show that our model outperforms the existing state-of-the-art models.

【 授权许可】

Unknown