j-hartmann/emotion-english-distilroberta-base is a forked repo from huggingface. License: None
Go to file
Hartmann ac484fe65a Update README.md 2021-06-17 09:07:25 +00:00
.gitattributes initial commit 2021-06-15 09:43:00 +00:00
README.md Update README.md 2021-06-17 09:07:25 +00:00
config.json updated labels 2021-06-15 10:33:11 +00:00
merges.txt initial commit 2021-06-15 09:55:44 +00:00
pytorch_model.bin initial commit 2021-06-15 09:55:44 +00:00
special_tokens_map.json initial commit 2021-06-15 09:55:44 +00:00
tokenizer.json initial commit 2021-06-15 09:55:44 +00:00
tokenizer_config.json initial commit 2021-06-15 09:55:44 +00:00
training_args.bin initial commit 2021-06-15 09:55:44 +00:00
vocab.json initial commit 2021-06-15 09:55:44 +00:00

README.md

language tags widget
en
sentiment
emotion
twitter
text
Oh wow. I didn't know that.
text
This movie always makes me cry..

Description

With this model, you can classify emotions in English text data. The model was trained on diverse datasets and predicts 7 emotions:

  1. anger
  2. disgust
  3. fear
  4. joy
  5. neutral
  6. sadness
  7. surprise

The model is a fine-tuned checkpoint of DistilRoBERTa-base.

Application

a) Run emotion model with 3 lines of code on single text example using Hugging Face's pipeline command on Google Colab:

Open In Colab

b) Run emotion model on multiple examples and full datasets (e.g., .csv files) on Google Colab:

Open In Colab

Contact

Please reach out to jochen.hartmann@uni-hamburg.de if you have any questions or feedback.

Thanks to Samuel Domdey and chrsiebert for their support in making this model available.

Appendix

Please find an overview of the datasets used for training below:

Name anger disgust
Crowdflower (2016) Yes Yes
McAuley and Leskovec (2013) (Reviews) 84.7 98.0
Average 78.1 93.2