Leveraging Deep Neural Networks for Aspect-Based Sentiment Classification

2025-03-17

AI Summary

To address the performance degradation in aspect-level sentiment classification caused by loss of edge information in syntactic dependency graphs, this paper proposes the Edge-Enhanced Graph Convolutional Network (EEGCN). Methodologically: (1) an edge-enhanced GCN is designed to explicitly model and preserve fine-grained features of syntactic dependency edges; (2) a hybrid encoder integrating Bi-LSTM and self-attention Transformer captures contextual semantics, while a bidirectional GCN models structural relationships among graph nodes; (3) an aspect-aware dynamic masking mechanism suppresses irrelevant dependency noise. The key contribution lies in being the first to incorporate explicit edge feature integrity modeling into the GCN architecture, enabling precise aspect–context alignment. EEGCN achieves significant improvements over state-of-the-art methods on four benchmark datasets. Ablation studies validate the effectiveness of each component, with particularly notable gains on complex syntactic structures and long-range dependencies.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Sentiment analysis and opinion mining

Abstract

Aspect-based sentiment analysis seeks to determine sentiment with a high level of detail. While graph convolutional networks (GCNs) are commonly used for extracting sentiment features, their straightforward use in syntactic feature extraction can lead to a loss of crucial information. This paper presents a novel edge-enhanced GCN, called EEGCN, which improves performance by preserving feature integrity as it processes syntactic graphs. We incorporate a bidirectional long short-term memory (Bi-LSTM) network alongside a self-attention-based transformer for effective text encoding, ensuring the retention of long-range dependencies. A bidirectional GCN (Bi-GCN) with message passing then captures the relationships between entities, while an aspect-specific masking technique removes extraneous information. Extensive evaluations and ablation studies on four benchmark datasets show that EEGCN significantly enhances aspect-based sentiment analysis, overcoming issues with syntactic feature extraction and advancing the field's methodologies.

Problem

• Improves syntactic feature extraction in sentiment analysis
• Enhances aspect-based sentiment classification accuracy
• Addresses loss of information in graph convolutional networks

Innovation

• Edge-enhanced GCN preserves syntactic feature integrity
• Bi-LSTM and transformer for effective text encoding
• Aspect-specific masking removes extraneous information