It is the nlp task to classify empathetic dialogues datasets using RoBERTa, ERNIE-2.0 and XLNet with different preprocessing method. You can get some detailed introduction and experimental results in the link below.

Predicting sentiment polarity of COVID-19 news articles using Machine Learning and Deep Learning models

RoBERTa and XLNet models to perform classification on the human emotion.

Review sentiment based on drug user reviews text/ dataset, using a supervised binary text classifier, which will classify user reviews as positive or negative