---
tags:
- setfit
- sentence-transformers
- text-classification
- generated_from_setfit_trainer
- Norway
- Cabinet Ministers
widget: []
metrics:
- accuracy
pipeline_tag: text-classification
library_name: setfit
inference: true
base_model: NbAiLab/nb-sbert-base
language:
- 'no'
- nb
---

# Purpose: Inform

This model has been trained on Facebook posts by Norwegian cabinet ministers of the Solberg governments (2013-2021). It was used in Karlsen, Kolltveit and Solheim (2025).
The posts were hand coded specifying different roles and purposes of the posts. 
Below, we recreate the table 1  from the paper showing the five roles and four purposes. The model included here identifies posts where the posts have the purpose of **Informing**. 
The setfit models that identify the other roles and purposes are available [here](https://huggingface.co/collections/oyvindbs/balancing-acts-the-communicative-roles-of-cabinet-ministers-68624b72c250c3cc1fd3ea14).
In the paper, we use one model for each purpose and each role. Each post can accordingly be ascribed to more than one purpose or role. 

|                              |     Communicative purposes    |                      |                   |                 |
|------------------------------|-------------------------------|----------------------|-------------------|-----------------|
|     **Communicative roles**      |     *Informing*                 |     Communication    |     Mobilizing    |     Branding    |
|     Ministry head            |                               |                      |                   |                 |
|     Cabinet member           |                               |                      |                   |                 |
|     Party politician         |                               |                      |                   |                 |
|     Individual politician    |                               |                      |                   |                 |
|     Private person           |                               |                      |                   |                 |

This is a [SetFit](https://github.com/huggingface/setfit) model that can be used for Text Classification of Norwegian social media posts. It uses [NbAiLab/nb-sbert-base](https://huggingface.co/NbAiLab/nb-sbert-base) as the Sentence Transformer embedding model. A [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance is used for classification.

It has been trained using an efficient few-shot learning technique that involves:

1. Fine-tuning a [Sentence Transformer](https://www.sbert.net) with contrastive learning.
2. Training a classification head with features from the fine-tuned Sentence Transformer.

## Model Details

### Model Description
- **Model Type:** SetFit
- **Sentence Transformer body:** [NbAiLab/nb-sbert-base](https://huggingface.co/NbAiLab/nb-sbert-base)
- **Classification head:** a [LogisticRegression](https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.LogisticRegression.html) instance
- **Maximum Sequence Length:** 75 tokens
- **Number of Classes:** 1
<!-- - **Training Dataset:** [Unknown](https://huggingface.co/datasets/unknown) -->

**Language:** 
* Norwegian (Bokmål)

<!-- - **License:** Unknown -->

### Model Sources

- **Repository:** [SetFit on GitHub](https://github.com/huggingface/setfit)
- **Paper:** [Efficient Few-Shot Learning Without Prompts](https://arxiv.org/abs/2209.11055)
- **Blogpost:** [SetFit: Efficient Few-Shot Learning Without Prompts](https://huggingface.co/blog/setfit)

## Uses

### Direct Use for Inference

First install the SetFit library:

```bash
pip install setfit
```

Then you can load this model and run inference.

```python
from setfit import SetFitModel

# Download from the 🤗 Hub
model = SetFitModel.from_pretrained("oyvindbs/setfit_minister_nb-sbert-base_Ministry-Head")
# Run inference
preds = model("I loved the spiderman movie!")
```

<!--
### Downstream Use

*List how someone could finetune this model on their own dataset.*
-->

<!--
### Out-of-Scope Use

*List how the model may foreseeably be misused and address what users ought not to do with the model.*
-->

<!--
## Bias, Risks and Limitations

*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.*
-->

<!--
### Recommendations

*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.*
-->

## Training Details

### Framework Versions
- Python: 3.10.4
- SetFit: 1.1.1
- Sentence Transformers: 3.4.1
- Transformers: 4.50.1
- PyTorch: 2.5.1+cu118
- Datasets: 2.19.0
- Tokenizers: 0.21.0

## Citation
```bibtex
@article{KarlsenKolltveitSolheim,
    author = {Karlsen, Rune and Kolltveit, Kristoffer and Solheim, Øyvind Bugge},
    title = {Balancing Acts: The communicative roles of cabinet ministers on social media},
    publisher = {Media and Communication},
    year = {2025},
    volume = {13},
    doi = {https://doi.org/10.17645/mac.10416}
}
```


### BibTeX
```bibtex
@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}
```

<!--
## Glossary

*Clearly define terms in order to be accessible across audiences.*
-->

<!--
## Model Card Authors

*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.*
-->

<!--
## Model Card Contact

*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.*
-->