Off_detection_turkish open-source model - Accurately detect offensive Turkish language, free to use!

Off Detection Turkish

Developed by hemekci

This is a Turkish offensive language detection model based on the BERT architecture, fine-tuned with Twitter data.

Downloads 131

Release Time : 3/2/2022

Model Overview

This model is used to detect offensive content in Turkish text, suitable for scenarios such as social media content moderation.

BERT-based architecture

Utilizes the powerful BERT model architecture with excellent text comprehension capabilities

Turkish language specialization

Specifically optimized and trained for the Turkish language

Trained on social media data

Fine-tuned with real Twitter data to adapt to social media contexts

Turkish text classification

Offensive content identification

Social media content analysis

Content moderation

Social media comment moderation

Automatically identifies offensive content in social media comments

Approximately 89% accuracy

Online community management

Helps community administrators quickly detect inappropriate remarks

epoch	Training Loss	Valid. Loss	Valid.Accuracy	Training Time	Validation Time
1	0.31	0.28	0.89	0:07:14	0:00:13
2	0.18	0.29	0.90	0:07:18	0:00:13
3	0.08	0.40	0.89	0:07:16	0:00:13
4	0.04	0.59	0.89	0:07:13	0:00:13

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base