Deep Learning for Aspect-Level Sentiment Classification: Survey, Vision, and Challenges

• Published in: IEEE access Vol. 7; pp. 78454 - 78483
• Main Authors: Zhou, Jie, Huang, Jimmy Xiangji, Chen, Qin, Hu, Qinmin Vivian, Wang, Tingting, He, Liang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aspect based sentiment analysis; aspect-level sentiment classification; attention; Benchmark testing; Classification; convolutional neural network (CNN); Datasets; Deep learning; Machine learning; Measurement; memory network; neural networks; Performance evaluation; recurrent neural network (RNN); Recurrent neural networks; Sentiment analysis; Standardization; State-of-the-art reviews; Taxonomy
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2920075

This survey focuses on deep learning-based aspect-level sentiment classification (ASC), which aims to decide the sentiment polarity for an aspect mentioned within the document. Along with the success of applying deep learning in many applications, deep learning-based ASC has attracted a lot of interest from both academia and industry in recent years. However, there still lack a systematic taxonomy of existing approaches and comparison of their performance, which are the gaps that our survey aims to fill. Furthermore, to quantitatively evaluate the performance of various approaches, the standardization of the evaluation methodology and shared datasets is necessary. In this paper, an in-depth overview of the current state-of-the-art deep learning-based methods is given, showing the tremendous progress that has already been made in ASC. In particular, first, a comprehensive review of recent research efforts on deep learning-based ASC is provided. More concretely, we design a taxonomy of deep learning-based ASC and provide a comprehensive summary of the state-of-the-art methods. Then, we collect all benchmark ASC datasets for researchers to study and conduct extensive experiments over five public standard datasets with various commonly used evaluation measures. Finally, we discuss some of the most challenging open problems and point out promising future research directions in this field.