Aspect-Level sentiment analysis based on fusion graph double convolutional neural networks

Abstract

Aspect-based sentiment analysis (ABSA) aims to analyze the emotional color contained in sentences or documents in more detail by classifying and evaluating different aspects and emotions in the text. However, the current research methods cannot effectively analyze the relationship between aspect words and context and extract grammatical information about sentences. Additionally, the extracted syntactic information is insufficient, and the combination of syntactic and semantic information is inefficient, leaving the model unable to correctly determine aspects' emotional orientations. This paper proposes an aspect-level sentiment analysis based on Fusion Graph Double Convolutional Neural Networks (FGD-GCN) to address these issues. Firstly, FGD-GCN proposes a multi-feature extraction module. Using BERT and bidirectional long-short-term memory models, this module extracts the hidden context between words. In addition, the positional attention module is used to capture important features in sentences, reducing noise and bias. Then, a semantic enhancement module is proposed, which fuses attention-focused information and feature information extracted from graphs to emphasize aspect words and context, and uses CNN model to classify on feature vectors. According to experiment results on three benchmark datasets, the model outperforms previous GCN methods for context-based aspect-level sentiment analysis.

GRAPHICAL ABSTRACT

Keywords:

• Graph convolutional network
• convolutional neural network
• aspect-based sentiment analysis
• BERT

Disclosure statement

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature or kind in any product, service and company that could be construed as influencing the position presented in, or the review of, the manuscript entitled.

Declaration of Data availability statement

This study was conducted with full access to all data, and I take full responsibility for the integrity of the data and the accuracy of the analysis.

Declaration of Ethical statement

This manuscript complies with the current laws of china.

Additional information

Funding

This work is supported by the Scientific Research Funds project of Science and Technology Department of Sichuan Province (Nos. 2019YFG0508,2019GFW131,2023JY**), Sichuan Key R&D project (No. 2023YFG0354), the National Natural Science Foundation of China (No. 61902324), Funds Project of Chengdu Science and Technology Bureau (Nos. 2017-RK00-00026-ZF,2022-YF04-00065-JH,2023-JB00-00020-GX), the Xihua University Education and teaching reform project (No: xjjg2021049,xjjg2021115), the National Natural Science Foundation of China (No. 61902324) and Science and Technology Planning Project of Guizhou Province (Nos. QianKeHeJiChu-ZK[2021]YiBan319).