Using Latent Fine-Grained Sentiment for Cross-Domain Sentiment Analysis

Kwun-Ping Lai, Jackie Chun-Sing Ho and Wai Lam
Additional contact information
Kwun-Ping Lai: The Chinese University of Hong Kong, Hong Kong
Jackie Chun-Sing Ho: The Chinese University of Hong Kong, Hong Kong
Wai Lam: The Chinese University of Hong Kong, Hong Kong

International Journal of Knowledge-Based Organizations (IJKBO), 2021, vol. 11, issue 3, 29-45

Abstract: The authors investigate the problem task of multi-source cross-domain sentiment classification under the constraint of little labeled data. The authors propose a novel model which is capable of capturing both sentiment terms with strong or weak polarity from various source domains which are useful for knowledge transfer to unlabeled target domain. The authors propose a two-step training strategy with different granularities helping the model to identify sentiment terms with different degrees of sentiment polarity. Specifically, the coarse-grained training step captures the strong sentiment terms from the whole review while the fine-grained training step focuses on the latent fine-grained sentence sentiment which are helpful under the constraint of little labeled data. Experiments on a real-world product review dataset show that the proposed model has a good performance even under the little labeled data constraint.

Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://services.igi-global.com/resolvedoi/resolve. ... 018/IJKBO.2021070103 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:igg:jkbo00:v:11:y:2021:i:3:p:29-45

Access Statistics for this article

International Journal of Knowledge-Based Organizations (IJKBO) is currently edited by John Wang

More articles in International Journal of Knowledge-Based Organizations (IJKBO) from IGI Global
Bibliographic data for series maintained by Journal Editor ().