Skip to main content

sbx-swe-sentiment_sentence-transformers-kblab_robust_swedish_sentiment_multiclass

Analysis citation Information

KB-Labb (2025). sbx-swe-sentiment_sentence-transformers-kblab_robust_swedish_sentiment_multiclass (updated: 2025-10-24). [Analysis]. Språkbanken Text. https://doi.org/10.23695/wh4w-na93
BibTeX Additional ways to cite the dataset.
Sentiment analysis per sentence using KBLab/robust-swedish-sentiment-multiclass

Sentiment analysis per sentence using transformers with KBLab/robust-swedish-sentiment-multiclass.

Example

This analysis is used with Sparv. Check out Sparv's quick start guide to get started!

To use this analysis, add the following line under export.annotations in the Sparv corpus configuration file:

- :sbx_sentiment_kb_sent.sentiment--kb-sent  # Sentiment analysis of sentence with KBLab/robust-swedish-sentiment-multiclass

You also need to install the following plugin: sbx_sentiment_kb_sent.

For general information on how to install plugins, see here.

For more info on how to use Sparv, check out the Sparv documentation.

Example output:


  Stora
  regnmängder
  väntas
  under
  måndagen
  och
  SMHI
  har
  utfärdat
  en
  gul
  varning
  för
  skyfallsliknande
  regn
  över
  stora
  delar
  av
  landets
  södra
  halva
  .

Type

  • Analysis

Task

  • sentiment analysis

Unit

  • sentence

Licence

Dependencies

External tools

Models

KBLab/robust-swedish-sentiment-multiclass
KBLab presents a robust, multi-label sentiment classifier trained on Swedish texts. The model is robust in the sense that it is trained on multiple datasets of different text types and allows labeling of neutral as well positive and negative texts.

Keyword

  • transformers
  • kb-lab

Creators

  • KB-Labb

Created

2024-05-28

Updated

2025-10-24

Contact

sb-info@svenska.gu.se