---
language:
  - en
tags:
  - IMF
  - sentiment
  - BERT
widget:
  - text: The new revenue administration combatted the underground economy.
---

**IMFBERT** is built by fine-tuning the 
[siebert/sentiment-roberta-large-english](https://huggingface.co/siebert/sentiment-roberta-large-english) 
model with IMF (International Monetary Fund) 
Executive Board meeting minutes (around 150,000 sentences). 
This model is suitable for English. Labels in this model are:
- 1 : Positive
- 0 : Negative


# Example Usage

```
from transformers import pipeline
sentiment_classification = pipeline(task = 'sentiment-analysis', model = 'faycadnz/IMFBERT_binary')
sentiment_classification('They remain vulnerable to external shocks.')
```


# Citation

If you find this repository useful in your research, please cite the following paper:

<ins>APA format</ins>:

> Deniz, A., Angin, M., & Angin, P. (2022, May). Understanding IMF Decision-Making with Sentiment Analysis. In 2022 30th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.

<ins>Bibtex format</ins>:

```
@inproceedings{deniz2022understanding,
  title={Understanding IMF Decision-Making with Sentiment Analysis},
  author={Deniz, Ay{\c{c}}a and Angin, Merih and Angin, Pelin},
  booktitle={2022 30th Signal Processing and Communications Applications Conference (SIU)},
  pages={1--4},
  year={2022},
  organization={IEEE}
}
```