Update README.md

README.md

@@ -1,3 +1,58 @@
----
-license: mit
----
+---
+license: mit
+language:
+- en
+---
+This is a BERT model trained on the U.S. Comparative Agendas Project (CAP) dataset, annotated with a top-level taxonomy covering 20 policy areas, as well as an "Others" category for non-policy-related text. The model is designed to identify policy and non-policy issues in political discourse.
+
+The performance of the model on an unseen test set is as follows:
+
+This is a BERT model trained on the US Comparative Agendas Project dataset for the U.S. with annotations for the top level taxonomy covering 20 policy areas and Others for non-policy related text.
+The model can be used to identify policy (non-policy)issues political discourse.
+
+## Model performance
+
+The model performance on unseen test set is as follows:
+
+<div align="center">
+  
+| Label                 |   F1 score |
+|:----------------------|-----------:|
+| Macroeconomics        |     0.8303 |
+| Civil rights          |     0.7676 |
+| Health                |     0.8886 |
+| Agriculture           |     0.8439 |
+| Labor                 |     0.7818 |
+| Education             |     0.9005 |
+| Environment           |     0.8481 |
+| Energy                |     0.8629 |
+| Immigration           |     0.8682 |
+| Transportation        |     0.8731 |
+| Law and crime         |     0.8207 |
+| Social welfare        |     0.7957 |
+| Housing               |     0.8462 |
+| Domestic commerce     |     0.8421 |
+| Defense               |     0.8627 |
+| Technology            |     0.8333 |
+| Foreign trade         |     0.8269 |
+| International affairs |     0.8907 |
+| Government operations |     0.8777 |
+| Public lands          |     0.8758 |
+| Others                |     0.6543 |
+| **Macro average**         |     **0.8573** |
+
+</div>
+
+
+This model was trained specifically for additional analyses presented in this [paper](https://doi.org/10.48550/arXiv.2405.07323).
+
+## Citation
+If you find this model useful for your work, please consider citing:
+```bibtex
+@article{aroyehun2024computational,
+  title={Computational analysis of US Congressional speeches reveals a shift from evidence to intuition},
+  author={Aroyehun, Segun Taofeek and Simchon, Almog and Carrella, Fabio and Lasser, Jana and Lewandowsky, Stephan and Garcia, David},
+  journal={arXiv preprint arXiv:2405.07323},
+  year={2024}
+}
+```