It is based on the pretrained
Danish BERT model by BotXO which has been fine-tuned on social media data.
This model should be used after detecting whether the text contains emotion or not, using the binary
BERT Emotion model.
1from transformers import BertTokenizer, BertForSequenceClassification
2
3model = BertForSequenceClassification.from_pretrained("alexandrainst/da-emotion-classification-base")
4tokenizer = BertTokenizer.from_pretrained("alexandrainst/da-emotion-classification-base")
The data used for training has not been made publicly available. It consists of social media data manually annotated in collaboration with Danmarks Radio.
