README.md

---
license: mit
language:
- hu
pipeline_tag: text-classification
datasets:
- tum-nlp/neural-news-benchmark
---

## Human written vs. AI written news classifier 
Trained on the Hungarian news data from:
https://huggingface.co/datasets/tum-nlp/neural_news

## Base model:
https://huggingface.co/google-bert/bert-base-multilingual-cased

## Data

See below for data splits:
![Data Splits](splits.png)

## Results

See below for accuracy metrics:
![Metrics](Metrics.png)

## Paper

```
@article{uyuk2024crafting,
  title={Crafting Tomorrow's Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian},
  author={{\"U}y{\"u}k, Cem and Rov{\'o}, Danica and Kolli, Shaghayegh and Varol, Rabia and Groh, Georg and Dementieva, Daryna},
  journal={arXiv preprint arXiv:2408.10724},
  year={2024}
}
```