sbx/KB-bert-base-swedish-cased_emotions_brighter

This model is for multi-label emotion classification of Swedish sentences. The model is fine-tuned on the Swedish subset of the Brigther dataset. Available labels:

• Anger
• Disgust
• Fear
• Joy
• Sadness
• Surprise

Example: 'Den här produkten lever inte alls upp till mina förväntningar, skäms!' Labels: |anger,0.97|disgust,0.97|surprise,0.35|

Model Details

Model Description

• Developed by: Språkbanken Text Shared by: Anna Lindahl (Annna)
• Model type: BERT for sentence classification
• Language(s): Swedish
• License: GPL-3.0
• Finetuned from model: KB/bert-base-swedish-cased

Training Data

The Swedish subset of the Brigther dataset. More information about the dataset can be found here:
BRIGHTER: BRIdging the Gap in Human-Annotated Textual Emotion Recognition Datasets for 28 Languages (Muhammad et al., ACL 2025)
SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection (Muhammad et al., SemEval 2025)

Model Card Authors

Anna Lindahl (Annna)