README.md

---
library_name: transformers
metrics:
- f1
base_model:
- allenai/specter2_base
model-index:
  - name: specter2-review-positive
    results:
      - task:
          type: text-classification
        dataset:
          name: validation
          type: validation
        metrics:
          - name: macro-average F1-score
            type: macro-average F1-score
            value: 0.89
---

# Model: specter2-review-positive

The model `snsf-data/specter2-review-positive` is based on the `allenai/specter2_base` model and **fine-tuned for a binary classification** task.
In particular, the model is fine-tuned to classify if a sentence from SNSF grant peer review report is addressing the following aspect:

***Is the sentence itself a positive statement or does it contain a positive statement?***

The model was fine-tuned based on a training set of 2'500 sentences from the SNSF grant peer review reports, which were manually annotated by multiple human annotators via majority rule.
The fine-tuning was performed locally without access to the internet to prevent any potential data leakage or network interference.
The following setup was used for the fine-tuning:

- Loss function: cross-entropy loss
- Optimizer: AdamW
- Weight decay: 0.01
- Learning rate: 2e-5
- Epochs: 3
- Batch size: 10
- GPU: NVIDIA RTX A2000

The model was then evaluated based on a validation set of 500 sentences, which were also manually annotated by multiple human annotators via majority rule.
The resulting macro-average **F1 score: 0.89** was achieved on the validation set. The share of the outcome label amounts to 37.1%.

The fine-tuning codes are open-sourced on GitHub: https://github.com/snsf-data/ml-peer-review-analysis .

Due to data privacy laws no data used for the fine-tuning can be publicly shared.
For a detailed description of data protection please refer to the data management plan underlying this work: https://doi.org/10.46446/DMP-peer-review-assessment-ML.
The annotation codebook is available online: https://doi.org/10.46446/Codebook-peer-review-assessment-ML.

For more details, see the the following preprint:

**A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports**

by [Gabriel Okasa](https://orcid.org/0000-0002-3573-7227),
[Alberto de León](https://orcid.org/0009-0002-0401-2618),
[Michaela Strinzel](https://orcid.org/0000-0003-3181-0623),
[Anne Jorstad](https://orcid.org/0000-0002-6438-1979),
[Katrin Milzow](https://orcid.org/0009-0002-8959-2534),
[Matthias Egger](https://orcid.org/0000-0001-7462-5132), and
[Stefan Müller](https://orcid.org/0000-0002-6315-4125), available on arXiv: https://arxiv.org/abs/2411.16662 .

## How to Get Started with the Model

The model can be used to classify sentences from grant peer review reports for addressing positive statements.

Use the code below to get started with the model.

```python
# import transformers library
import transformers

# load tokenizer from specter2_base - the base model
tokenizer = transformers.AutoTokenizer.from_pretrained("allenai/specter2_base")

# load the SNSF fine-tuned model for classification of positive statements in review texts
model = transformers.AutoModelForSequenceClassification.from_pretrained("snsf-data/specter2-review-positive")

# setup the classification pipeline
classification_pipeline = transformers.TextClassificationPipeline(
    model=model,
    tokenizer=tokenizer,
    return_all_scores=True
)

# prediction for an example review sentence addressing positive statement
classification_pipeline("The strengths of this proposal are the strong applicant and team, the current dynamic nature of the field under study, and the potential impact of the work on advancing biological understanding and clinical care.")

# prediction for an example review sentence not addressing positive statement
classification_pipeline("There are currently several activities on an international level that have identified the issue and activities are underway.")
```

## Model Limitations
- *Human Assessment Required*: This model should not be used for automatic classification of grant peer review reports without human oversight.
- *Limited Training Data*: The model was fine-tuned on a limited sample of 2,500 annotated sentences. Therefore, its classification accuracy should be critically evaluated before deployment.
- *Specific Training Data*: The training data consists of a random sample of SNSF grant peer review reports. As such, the model's external validity to other datasets may be limited.

## Citation

**BibTeX:**

```bibtex
@article{okasa2024supervised,
  title={A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports},
  author={Okasa, Gabriel and de Le{\'o}n, Alberto and Strinzel, Michaela and Jorstad, Anne and Milzow, Katrin and Egger, Matthias and M{\"u}ller, Stefan},
  journal={arXiv preprint arXiv:2411.16662},
  year={2024}
}
```

**APA:**

Okasa, G., de León, A., Strinzel, M., Jorstad, A., Milzow, K., Egger, M., & Müller, S. (2024). A Supervised Machine Learning Approach for Assessing Grant Peer Review Reports. arXiv preprint arXiv:2411.16662.

## Model Card Authors

[Gabriel Okasa](https://orcid.org/0000-0002-3573-7227),
[Alberto de León](https://orcid.org/0009-0002-0401-2618),
[Michaela Strinzel](https://orcid.org/0000-0003-3181-0623),
[Anne Jorstad](https://orcid.org/0000-0002-6438-1979),
[Katrin Milzow](https://orcid.org/0009-0002-8959-2534),
[Matthias Egger](https://orcid.org/0000-0001-7462-5132), and
[Stefan Müller](https://orcid.org/0000-0002-6315-4125)

## Model Card Contact

[email protected]