Recent advances in deep learning based sentiment analysis
- PDF / 1,995,661 Bytes
- 24 Pages / 612 x 792 pts (letter) Page_size
- 1 Downloads / 195 Views
Print-CrossMark
https://doi.org/10.1007/s11431-020-1634-3
Special Topic: Natural Language Processing Technology
. Review .
Recent advances in deep learning based sentiment analysis YUAN JianHua1, WU Yang1, LU Xin1, ZHAO YanYan1* , QIN Bing1,2 & LIU Ting1 1 Research
Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin 150001, China; 2 Pengcheng Lab, Shenzhen 518066, China Received March 9, 2020; accepted May 11, 2020; published online September 15, 2020
Sentiment analysis is one of the most popular research areas in natural language processing. It is extremely useful in many applications, such as social media monitoring and e-commerce. Recent application of deep learning based methods has dramatically changed the research strategies and improved the performance of many traditional sentiment analysis tasks, such as sentiment classification and aspect based sentiment analysis. Moreover, it also pushed the boundary of various sentiment analysis task, including sentiment classification of different text granularities and in different application scenarios, implicit sentiment analysis, multimodal sentiment analysis and generation of sentiment-bearing text. In this paper, we give a brief introduction to the recent advance of the deep learning-based methods in these sentiment analysis tasks, including summarizing the approaches and analyzing the dataset. This survey can be well suited for the researchers studying in this field as well as the researchers entering the field. coarse-grained, fine-grained, implicit, multi-modal, generation Citation:
Yuan J H, Wu Y, Lu X, et al. Recent advances in deep learning based sentiment analysis. Sci China Tech Sci, 2020, 63, https://doi.org/10.1007/s11431020-1634-3
1 Introduction Sentiment floods our everyday life: people tweet and express opinions on their daily life and hot topics, consumer read product review before shopping and write reviews after experiencing product or service, retailer and manufactures improve their products or service through surveying and analyzing people’s opinions, and etc. Thus, mining the sentiment exists in these user-generated contents has been a hot research topic in natural language processing, data mining, web mining and social media analysis, drawing growing attention from both research and industry communities during the past two decades. Before the era of deep learning, machine learning based methods with rich hand-craft features dominate the field of natural language processing as well as sentiment analysis. *Corresponding author (email: [email protected])
Since the past decades, neural network-based feature extractors [1, 2] have become predominant for their superior ability in automatically extracting meaningful and abstract semantic features for sentiment analysis, which take place of previous sparse and high-dimensional feature engineering based methods. In this paper, we introduce common and practical structures used for deep learning-based sentiment analysis tasks as well as specialty of sent
Data Loading...
