Aspect-based sentiment analysis via multitask learning for online reviews

Abstract

Aspect based sentiment analysis(ABSA) aims to identify aspect terms in online reviews and predict their corresponding sentiment polarity. Sentiment analysis poses a challenging fine-grained task. Two typical subtasks are involved: Aspect Term Extraction (ATE) and Aspect Polarity Classification (APC). These two subtasks are usually trained discretely, which ignores the connection between ATE and APC. Concretely, we can relate ATE to APC through aspects and train them concurrently. We mainly use the ATE task as an auxiliary task, allowing the APC to focus more on relevant aspects to facilitate aspect polarity classification. In addition, previous studies have shown that utilizing dependency syntax information with a graph neural network (GNN) also contributes to the performance of the APC task. However, most studies directly input sentence dependency relations into graph neural networks without considering the influence of aspects, which do not emphasize the important dependency relationships. To address these issues, we propose a multitask learning model combining APC and ATE tasks that can extract aspect terms as well as classify aspect polarity simultaneously. Moreover, we exploit multihead attention(MHA) to associate dependency sequences with aspect extraction, which not only combines both ATE and APC tasks but also stresses the significant dependency relations, enabling the model to focus more on words closely related to aspects. According to our experiments on three benchmark datasets, we demonstrate that the connection between ATE and APC can be better established by our model, which enhances aspect polarity classification performance significantly. The source code has been released on GitHub https://github.com/winder-source/MTABSA.