Contrastive transformer based domain adaptation for multi-source cross-domain sentiment classification

作者：

Highlights：

• We discussed the selection strategy of multi-source domains to optimize data quality.

• We proposed a domain adaptor and discriminator for the sentiment transfer.

• Implementations have been carried out in the combination of source classifiers.

摘要

•We discussed the selection strategy of multi-source domains to optimize data quality.•We proposed a domain adaptor and discriminator for the sentiment transfer.•Implementations have been carried out in the combination of source classifiers.

论文关键词：Sentiment classification,Contrastive learning,Domain adaptation,Multi-source domains

论文评审过程：Received 31 August 2021, Revised 17 February 2022, Accepted 23 March 2022, Available online 29 March 2022, Version of Record 8 April 2022.

论文官网地址：https://doi.org/10.1016/j.knosys.2022.108649