Turkish Toxic Language Detection

🚀 Turkish Toxic Language Detection Model

This model is a fine - tuned version of dbmdz/bert-base-turkish-cased for binary toxicity classification in Turkish text. It was trained using a cleaned and preprocessed version of the Overfit-GM/turkish-toxic-language dataset.

✨ Features

• Accurate Classification: Achieves high accuracy, F1 - score, precision, and recall in classifying toxic and non - toxic Turkish text.
• Cleaned Data Training: Trained on preprocessed text with basic cleaning and slang filtering.

📦 Installation

No specific installation steps are provided in the original README. So, this section is skipped.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

tokenizer = AutoTokenizer.from_pretrained("fc63/turkish_toxic_language_detection_model")
model = AutoModelForSequenceClassification.from_pretrained("fc63/turkish_toxic_language_detection_model")

def predict_toxicity(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding="max_length", max_length=128)
    outputs = model(**inputs)
    predicted = torch.argmax(outputs.logits, dim=1).item()
    return "Toxic" if predicted == 1 else "Non-Toxic"

📚 Documentation

Performance

Confusion Matrix

Preprocessing Details (cleaned_corrected_text)

The model is trained on the cleaned_corrected_text column, which is derived from corrected_text using basic regex - based cleaning steps and manual slang filtering.

Cleaning Function

def clean_corrected_text(text):
    text = text.lower()
    text = re.sub(r"http\S+|www\S+|https\S+", '', text, flags=re.MULTILINE)  # URL removal
    text = re.sub(r"@\w+", '', text)  # remove @mentions
    text = re.sub(r"[^\w\s.,!?-]", '', text)  # remove special characters (e.g., emojis)
    text = re.sub(r"\s+", ' ', text).strip()  # normalize whitespaces
    return text

Manual Slang Filtering

slang_words = ["kanka", "lan", "knk", "bro", "la", "birader", "kanki"]

def remove_slang(text):
    for word in slang_words:
        text = text.replace(word, "")
    return text.strip()

Applied Steps Summary

Conclusion: cleaned_corrected_text is a lightly cleaned, non - linguistically processed text column. The model is trained directly on this.

Training Details

• Trainer: Hugging Face Trainer API
• Epochs: 3
• Batch size: 16
• Learning Rate: 2e - 5
• Eval Strategy: Epoch - based
• Undersampling: Applied to balance class distribution

Dataset

Dataset used: Overfit-GM/turkish-toxic-language
Final dataset size after preprocessing and balancing: 54068 samples

🔧 Technical Details

The model is a fine - tuned version of dbmdz/bert-base-turkish-cased for binary toxicity classification in Turkish text. It uses basic regex - based cleaning and manual slang filtering for preprocessing. The training is done using the Hugging Face Trainer API with specific hyperparameters and undersampling to balance the class distribution.

📄 License

This project is licensed under the MIT license.