Deep learning for aspect-based sentiment analysis: a review

Linan Zhu; Minhao Xu; Yinwei Bao; Yifei Xu; Xiangjie Kong

doi:10.7717/peerj-cs.1044

Deep learning for aspect-based sentiment analysis: a review

PeerJ Comput Sci. 2022 Jul 19:8:e1044. doi: 10.7717/peerj-cs.1044. eCollection 2022.

Authors

Linan Zhu¹, Minhao Xu¹, Yinwei Bao¹, Yifei Xu¹, Xiangjie Kong¹

Affiliation

¹ College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China.

Abstract

User-generated content on various Internet platforms is growing explosively, and contains valuable information that helps decision-making. However, extracting this information accurately is still a challenge since there are massive amounts of data. Thereinto, sentiment analysis solves this problem by identifying people's sentiments towards the opinion target. This article aims to provide an overview of deep learning for aspect-based sentiment analysis. Firstly, we give a brief introduction to the aspect-based sentiment analysis (ABSA) task. Then, we present the overall framework of the ABSA task from two different perspectives: significant subtasks and the task modeling process. Finally, challenges are proposed and summarized in the field of sentiment analysis, especially in the domain of aspect-based sentiment analysis. In addition, ABSA task also takes the relations between various objects into consideration, which is rarely discussed in the previous work.

Keywords: Aspect-based sentiment analysis; Deep learning; Multi-task learning; Relation extraction.

Grants and funding

This work was supported by the National Natural Science Foundation of China (No. 62176234, 62072409, 61701443). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.