metadata
license: mit
datasets:
- nanelimon/insult-dataset
language:
- tr
pipeline_tag: text-classification
About the model
It is a Turkish bert-based model created to determine the types of bullying that people use against each other in social media. Included classes;
- Nötr
- Kızdırma/Hakaret
- Cinsiyetçilik
- Irkçılık
3388 tweets were used in the training of the model. Accordingly, the success rates in education are as follows;
| INSULT | OTHER | PROFANITY | RACIST | SEXIST | |
|---|---|---|---|---|---|
| Precision | 0.901 | 0.924 | 0.978 | 1.000 | 0.980 |
| Recall | 0.920 | 0.980 | 0.900 | 0.980 | 1.000 |
| F1 Score | 0.910 | 0.9514 | 0.937 | 0.989 | 0.990 |
- F-Score: 0.9559690799177005
- Recall: 0.9559999999999998
- Precision: 0.9570284225256961
- Accuracy: 0.956
Dependency
pip install torch torchvision torchaudio
pip install tf-keras
pip install transformers
pip install tensorflow
Example
from transformers import AutoTokenizer, TextClassificationPipeline, TFBertForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("nanelimon/bert-base-turkish-offensive")
model = TFBertForSequenceClassification.from_pretrained("nanelimon/bert-base-turkish-offensive", from_pt=True)
pipe = TextClassificationPipeline(model=model, tokenizer=tokenizer, return_all_scores=True, top_k=2)
print(pipe('Bu bir denemedir hadi sende dene!'))
Result;
[[{'label': 'OTHER', 'score': 1.000}, {'label': 'INSULT', 'score': 0.000}]]
- label= It shows which class the sent Turkish text belongs to according to the model.
- score= It shows the compliance rate of the Turkish text sent to the label found.
Authors
- Seyma SARIGIL: [email protected]
License
gpl-3.0
Free Software, Hell Yeah!