|
--- |
|
license: mit |
|
datasets: |
|
- mlburnham/PoliStance_Affect |
|
- mlburnham/PoliStance_Affect_QT |
|
pipeline_tag: zero-shot-classification |
|
language: |
|
- en |
|
library_name: transformers |
|
tags: |
|
- Politics |
|
- Twitter |
|
--- |
|
# Model Description |
|
This model adapts [Moritz Laurer's](https://huggingface.co/MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 ) zero shot model for political texts. |
|
It is currently trained for zero-shot classification of stances towards political groups and people, although it should also preform well for topic and issue stance classification. |
|
Further capabilities will be added and benchmarked as more training data is developed. |
|
|
|
# Training Data |
|
The model was trained using the [PoliStance Affect](https://huggingface.co/datasets/mlburnham/PoliStance_Affect) and [PoliStance Affect_QT](https://huggingface.co/datasets/mlburnham/PoliStance_Affect_QT) datasets. |
|
- Polistance Affect: ~27,000 political texts about U.S. politicians and political groups that have been triple coded for stance. |
|
- Polistance Affect QT: A set of quote tweets about U.S. politicians that pose a particularly challenging classification task. |
|
|
|
The test set for both datasets contains documents about six politicians that were not included in the training set in order to evaluate zero-shot classification performance. |
|
|
|
# Evaluation |
|
Results below are performance on the PoliStance Affect test set. |
|
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d0341901931c60161f2a06/NLJtILuPLKtxN0bJJwD0C.png" width="750" height="500" /> |
|
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/64d0341901931c60161f2a06/4tOqiINS6BWItRklrqkgY.png" width="750" height="500" /> |
