---
language: en
license: apache-2.0
datasets:
- ESGBERT/governance_data
tags:
- ESG
- governance
---

# Model Card for GovRoBERTa-base

## Model Description

Based on [this paper](https://www.sciencedirect.com/science/article/pii/S1544612324000096), this is the GovRoBERTa-base language model. A language model that is trained to better understand governance texts in the ESG domain.

*Note: We generally recommend choosing the [GovernanceBERT-base](https://huggingface.co/ESGBERT/GovernanceBERT-base) model since it is quicker, less resource-intensive and only marginally worse in performance.*

Using the [RoBERTa](https://huggingface.co/roberta-base) model as a starting point, the GovRoBERTa-base Language Model is additionally pre-trained on a text corpus comprising governance-related annual reports, sustainability reports, and corporate and general news.

## More details can be found in the paper
```bibtex
@article{schimanski_ESGBERT_2024,
title = {Bridging the gap in ESG measurement: Using NLP to quantify environmental, social, and governance communication},
journal = {Finance Research Letters},
volume = {61},
pages = {104979},
year = {2024},
issn = {1544-6123},
doi = {https://doi.org/10.1016/j.frl.2024.104979},
url = {https://www.sciencedirect.com/science/article/pii/S1544612324000096},
author = {Tobias Schimanski and Andrin Reding and Nico Reding and Julia Bingler and Mathias Kraus and Markus Leippold},
}
```