language: - tr tags: - text-classification - emotion - pytorch datasets: - emotion metrics: - Accuracy, F1 Score

bert-base-turkish-cased-emotion

Model description:

bert-base-turkish-cased finetuned on Turkish film comments shared in beyazperde.com with the help of BERTurk pretrained language model using PyTorch and Huggingface Transformers library.

 learning rate 2e-5, 
 batch size 32,
 num_train_epochs=5,
 optimizer=AdamW

Model Performance

precision recall f1-score support

       0       0.93      0.93      0.93      1333
       1       0.93      0.93      0.93      1333

accuracy                           0.93      2666

macro avg 0.93 0.93 0.93 2666 weighted avg 0.93 0.93 0.93 2666

How to Use the model:

from transformers import pipeline
classifier = pipeline("text-classification",
                       model='zafercavdar/distilbert-base-turkish-cased-emotion',
                       return_all_scores=True)
prediction = classifier("Bu kütüphaneyi seviyorum, en iyi yanı kolay kullanımı.", )
print(prediction)

"""
Output:
[
  [
    {'label': 'sadness', 'score': 0.0026786490343511105},
    {'label': 'joy', 'score': 0.6600754261016846},
    {'label': 'love', 'score': 0.3203163146972656},
    {'label': 'anger', 'score': 0.004358913749456406},
    {'label': 'fear', 'score': 0.002354539930820465},
    {'label': 'surprise', 'score': 0.010216088965535164}
  ]
]

"""

Dataset:

Beyazoerde.com reviews.