Hate Trained 31415
H
Hate Trained 31415
Developed by marcolatella
Hate speech detection model fine-tuned on distilbert-base-uncased, trained on tweet_eval dataset
Downloads 15
Release Time : 3/2/2022
Model Overview
This model is specifically designed to identify hate speech in tweets, suitable for social media content moderation scenarios
Model Features
Efficient and lightweight
Based on DistilBERT architecture, reducing model size while maintaining performance
High accuracy
Achieves an F1 score of 0.7719 on the tweet_eval dataset
Social media optimized
Specifically trained for tweet content, suitable for social media scenarios
Model Capabilities
Text classification
Hate speech detection
Social media content analysis
Use Cases
Content moderation
Automatic hate speech detection
Automatically identify hate speech content on social media
F1 score 0.7719
Social media analysis
Tweet sentiment analysis
Analyze hateful content in tweets
Featured Recommended AI Models
Š 2025AIbase