关键词: 关键词: 自然语言处理, 方面级情感分析, 图卷积网络, 双仿射注意力, 平均池化

Abstract: Abstract: Aspect-Based Sentiment Analysis（ABSA）is a fine-grained sentiment analysis task aims to analyze the sentiment polarity of specific aspect words in a given text. Existing ABSA methods used Graph Convolutional Network(GCN) to process syntactic and semantic information, but they treated all syntactic dependencies of aspect words equally, ignoring the impact of distant unrelated words on target aspect words, resulting in inappropriate weight allocation of target aspect words and viewpoint words, and insufficient extraction of semantic information. A aspect-based sentiment analysis model integrating syntax and sentiment knowledge was proposed to address this issue. first, a reachability matrix was constructed based on syntactic information. Based on this, a syntactic enhancement graph was constructed by weighting the central position of aspect words Then, a semantic enhancement graph was constructed through external emotional knowledge and aspect enhancement. Graph convolution was used to fully model the syntactic enhancement graph and semantic enhancement graph to form different feature channels. Next, biaffine Attention was used to effectively integrate syntactic and semantic information. Finally, average-pooling and concatenation operations were used to obtain the final feature vector corresponding to aspect words. Compared with the Deep Dependent Perception Graph Convolutional Network (DA-GCN-BERT), the proposed model achieved accuracy improvements of 1.71, 1.41, 1.27, 0.17, and 0.43 percentage points on five publicly available datasets, respectively. The experimental results indicate that the proposed model has strong applicability in the field of aspect-based sentiment analysis.

Key words: Keywords: Natural Language Processing(NLP), Aspect-based Sentiment Analysis(ABSA), Graph Convolutional Network(GCN), biAffine attention, average-pooling