TS-GCN: Aspect-level sentiment classification model for consumer reviews

Abstract

The goal of aspect-level sentiment classification (ASC) task is to obtain the sentiment polarity of aspect words in the text. Most existing methods ignore the implicit aspects, resulting in low classification accuracy. To improve the accuracy, this paper proposes a classification model for consumer reviews, abbreviated as TS-GCN (Truncated history attention and Selective transformation network-Graph Convolutional Networks). TS-GCN can classify sentiment from both explicit and implicit aspects. Firstly, we process the text by the BERT model and the BiLSTM model to obtain the text features. Secondly, the GCN model completes explicit sentiment classification by training text features. Due to the lack of implicit words, the GCN model cannot classify implicit sentiments. Finally, we predict implicit words based on the TS model, which makes up for the deficiency of the GCN model and completes the sentiment classification of implicit words. TS-GCN is proved on several datasets in the consumer reviews field. The results of experiments show that the TS-GCN can improve the accuracy and F1 of ASC.

Chinese text dual attention network for aspect-level sentiment classification

“…This approach promotes the sentimental classification of aspect-level. Graph convolutional neural networks (GCNs) [ 39 ] and BERT [ 40 ] models have exhibited remarkable performance in text and sentiment classification. For instance, Wang et al [ 41 ] proposed the KGBGCN model, which effectively addresses the challenge of capturing key information in lengthy documents and overcoming the deficiency in classification accuracy due to the lack of domain-specific knowledge.…”

Aspect Sentiment Triplet Extraction Based on Deep Relationship Enhancement Networks

“…Fan et al [13] argued that when both aspect words and contexts are long, the simplicity of the weighted sum attention mechanism would introduce some noise; thus, they proposed a multi-granularity attention mechanism to reduce irrelevant information. Since the application of BERT and GCN in the field of NLP, a large number of works based on BERT and GCN have also studied ABSA, such as Zhou et al [10] and Zhang et al [14].…”