A Survey of Sentiment Analysis Based on Pretrained Language Models

Pretrained Language Models (PLMs) can be applied to downstream tasks with only fine-tuning, without learning the model from scratch. In particular, PLMs have been applied to Sentiment Analysis (SA), which detects, analyses, and extracts the polarity of the sentiment expressed in texts. To help researchers quickly grasp the state-of-art PLM-based SA, we survey PLM-based methods for mono-lingual and cross-lingual SA in this paper. Specifically, we brief these methods, compare their per-formance and point out the challenges for future research.