Targeted sentiment classification aims to predict the emotional trend of a specific goal. Currently, most methods (e.g., recurrent neural networks and convolutional neural networks combined with an attention mechanism) are not able to fully capture the semantic information of the context and they also lack a mechanism to explain the relevant syntactical constraints and long-range word dependencies. Therefore, syntactically irrelevant context words may mistakenly be recognized as clues to predict the target sentiment. To tackle these problems, this paper considers that the semantic information, syntactic information, and their interaction information are very crucial to targeted sentiment analysis, and propose an attentional-encoding-based graph convolutional network (AEGCN) model. Our proposed model is mainly composed of multi-head attention and an improved graph convolutional network built over the dependency tree of a sentence. Pre-trained BERT is applied to this task, and new state-of-art performance is achieved. Experiments on five datasets show the effectiveness of the model proposed in this paper compared with a series of the latest models.

Luwei Xiao, Rui Mao, Xulang Zhang, Liang He, Erik Cambria. Findings of the Association for Computational Linguistics: EMNLP 2024. 2024.