This RoBERTa-based model can classify the sentiment of English language text in 3 classes:

• positive ?
• neutral ?
• negative ?

The model was fine-tuned on 5,304 manually annotated social media posts. The hold-out accuracy is 86.1%. For details on the training approach see Web Appendix F in Hartmann et al. (2021).

Application

from transformers import pipeline
classifier = pipeline("text-classification", model="j-hartmann/sentiment-roberta-large-english-3-classes", return_all_scores=True)
classifier("This is so nice!")

Output:
[[{'label': 'negative', 'score': 0.00016451838018838316},
  {'label': 'neutral', 'score': 0.000174045650055632},
  {'label': 'positive', 'score': 0.9996614456176758}]]

Reference

Please cite this paper when you use our model. Feel free to reach out to jochen.hartmann@tum.de with any questions or feedback you may have.

@article{hartmann2021,
  title={The Power of Brand Selfies},
  author={Hartmann, Jochen and Heitmann, Mark and Schamp, Christina and Netzer, Oded},
  journal={Journal of Marketing Research}
  year={2021}
}