---
language:
- en
tags:
- Twitter
- Climate Change
license: mit
---
# Model Card Climate-TwitterBERT-step-2 

## Overview:

Using Climate-TwitterBERT-step-1 (https://huggingface.co/Climate-TwitterBERT/Climate-TwitterBERT-step1) as the starting model, we fine-tuned on the downstream task to classify whether a given climate tweet belongs to hard/soft/promotion climate tweet.

The model provides a label and probability score, indicating whether a given tweet belongs to hard (label = 0), soft (label = 1), or promotion (label = 2).

## Performance metrics:

Based on the test set, the model achieves the following results:

•	Loss: 0.2613
•	F1-weighted: 0.8008     
•	F1: 0.7798
•	Accuracy: 0.8050
•	Precision: 0.8034
•	Recall: 0.8050

## Example usage:

```python
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification

task_name = 'text-classification'
model_name = 'Climate-TwitterBERT/ Climate-TwitterBERT-step2'

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSequenceClassification.from_pretrained(model_name)

pipe = pipeline(task=task_name, model=model, tokenizer=tokenizer)

tweet = "We are committed to significantly cutting our carbon emissions by 30% before 2030."
result = pipe(tweet)
# The 'result' variable will contain the classification output: 0 = hard climate tweet, 1= soft climate tweet, and 2 = promotion tweet.
```

## Citation: 

```bibtex
@article{fzz2025climatetwitter,
  title={Responding to Climate Change Crisis: Firms' Tradeoffs},
  author={Fritsch, Felix and Zhang, Qi and Zheng, Xiang},
  journal={Journal of Accounting Research},
  year={2025},
  doi={10.1111/1475-679X.12625}
}

```

Fritsch, F., Zhang, Q., & Zheng, X. (2025). Responding to Climate Change Crisis: Firms' Tradeoffs. Journal of Accounting Research. https://doi.org/10.1111/1475-679X.12625


## Framework versions
•	Transformers 4.28.1
•	Pytorch 2.0.1+cu118
•	Datasets 2.14.1
•	Tokenizers 0.13.3