Aspect-Aware Graph Interaction Attention Network for Aspect Category Sentiment Analysis

Pengfei Yu, Jingjing Gu, Dechang Pi, Qiang Zhou, Qiuhong Wang

Abstract: This paper explores an implicit Aspect Category Sentiment Analysis task, which aims to determine the sentiment polarities of given aspect categories in social reviews. Currently, most researchers focus more on explicit aspect and rarely work on implicit aspect. Meanwhile, due to the semantic complexity of natural language, it is difficult for existing methods to retrieve such implicit semantics in sentences. To this end, we propose a novel framework, the Aspect-aware Graph Interaction Attention Network (AGIAN), which concentrates on aspect-related information implicitly in sentences and identifies its corresponding sentiment polarity. Specifically, first, we introduce an aspect-aware graph to represent potential associations between the implicit aspect category and the sentence. Then, we utilize two types of graph neural networks to extract rich relational semantics. Finally, we design a graph interaction mechanism to integrate sentiment features specific to the aspect category for sentiment classification. We evaluate the performance of the proposed framework on six publicly available benchmark datasets. Extensive experiments demonstrate that, compared to some competitive baseline methods, AGIAN can effectively improve accuracy and achieve state-of-the-art performance on the F1-score.