MARBERT Sarcasm Detector

This model is fine-tuned UBC-NLP/MARBERTv2 was finetuned on ArSarcasT corpus training dataset. It achieves the following results on the evaluation sets:

Eval Datatset	Accuracy	F1	Precision	Recall
ArSarcasT	0.844	0.735	0.754	0.718
iSarcasmEVAL	0.892	0.633	0.616	0.650
ArSarcasmV2	0.771	0.561	0.590	0.534

Model description

Fine-tuned MARBERT-v2 model on Sarcastic tweets dataset for sarcasm detection text classification.

Intended uses & limitations

More information needed

Training and evaluation data

Training dataset: ArSarcasT development split.
Evaluation Datasets:
- ArSarcasm-v2 test dataset.
- iSarcasmEVAL test dataset.
- ArSarcasT test dataset.

Training procedure

Fine-tuning, 3 epochs

Training hyperparameters

The following hyperparameters were used during training:

optimizer: None
training_precision: float32

Training results

Framework versions

Transformers 4.28.1
TensorFlow 2.12.0
Tokenizers 0.13.3

Paper Citation

If you use this fine-tuned model based on the original MARBERT model, please cite the following paper: Galal, M. A., Yousef, A. H., Zayed, H. H., & Medhat, W. (2024). Arabic sarcasm detection: An enhanced fine-tuned language model approach. Ain Shams Engineering Journal, 15(6), 102736. https://doi.org/10.1016/j.asej.2024.102736 (https://www.sciencedirect.com/science/article/pii/S2090447924001114)

Dataset Repository

https://github.com/Mabdelaziz/ArSarcasT.git

Downloads last month: 4