ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 2069–2079 June 6–11, 2021. ©2021 Association for Computational Linguistics 2069 ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction Jiahao Bu1∗, Lei Ren1∗, Shuang Zheng1,2∗, Yang Yang1, Jingang Wang1†, Fuzheng Zhang1, Wei Wu1 1Meituan, Beijing, China 2School of Economics and Management, Dalian University of Technology, Dalian, China {bujiahao,renlei04,zhengshuang04,yangyang113}@meituan.com {wangjingang02,zhangfuzheng,wuwei30}@meituan.com Abstract Sentiment analysis has attracted increasing at- tention in e-commerce. The sentiment polari- ties underlying user reviews are of great value for business intelligence. Aspect category sen- timent analysis (ACSA) and review rating pre- diction (RP) are two essential tasks to detect the fine-to-coarse sentiment polarities. ACSA and RP are highly correlated and usually em- ployed jointly in real-world e-commerce sce- narios. While most public datasets are con- structed for ACSA and RP separately, which may limit the further exploitations of both tasks. To address the problem and advance re- lated researches, we present a large-scale Chi- nese restaurant review dataset ASAP includ- ing 46, 730 genuine reviews from a leading online-to-offline (O2O) e-commerce platform in China. Besides a 5-star scale rating, each review is manually annotated according to its sentiment polarities towards 18 pre-defined as- pect categories. We hope the release of the dataset could shed some light on the field of sentiment analysis. Moreover, we propose an intuitive yet effective joint model for ACSA and RP. Experimental results demonstrate that the joint model outperforms state-of-the-art baselines on both tasks. 1 Introduction With the rapid development of e-commerce, mas- sive user reviews available on e-commerce plat- forms are becoming valuable resources for both customers and merchants. Aspect-based sentiment analysis(ABSA) on user reviews is a fundamental and challenging task which attracts interests from both academia and industries (Hu and Liu, 2004; Ganu et al., 2009; Jo and Oh, 2011; Kiritchenko et al., 2014). According to whether the aspect terms are explicitly mentioned in texts, ABSA can be further classified into aspect term sentiment anal- ∗Equal contribution. †Corresponding author. ysis (ATSA) and aspect category sentiment analy- sis (ACSA), we focus on the latter which is more widely used in industries. Specifically, given a re- view ”Although the fish is delicious, the waiter is horrible!”, the ACSA task aims to infer the senti- ment polarity over aspect category food is positive while the opinion over the aspect category service is negative. The user interfaces of e-commerce platforms are more intelligent than ever before with the help of ACSA techniques. For example, Figure 1 presents the detail page of a coffee shop on a popular e- commerce platform in China. The upper aspect- based sentiment text-boxes display the aspect cate- gories (e.g., food, sanitation) mentioned frequently in user reviews and the aggregated sentiment po- larities on these aspect categories (the orange ones represent positive and the blue ones represent neg- ative). Customers can focus on corresponding re- views effectively by clicking the aspect-based sen- timent text-boxes they care about (e.g., …

Content truncated to 500 words