Tanat05/korcen-kogpt2

Korean deeplearning swear word(딥러닝 기반 욕설/비속어 판별)

24
/ 100
Experimental

This project helps online community managers, social media moderators, or customer service teams automatically identify and filter Korean abusive or hateful language. It takes Korean text as input and intelligently detects offensive content by analyzing context and linguistic patterns, providing a judgment on whether the text contains abusive language. This is for anyone managing user-generated content in Korean who needs to maintain a positive and safe online environment.

No commits in the last 6 months.

Use this if you need a more accurate, context-aware solution for filtering Korean profanity and hate speech than simple keyword blocking.

Not ideal if your primary need is filtering non-Korean languages or if you require fine-grained sentiment analysis beyond simple abuse detection.

content-moderation online-community-management korean-language-processing brand-reputation-management customer-service
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

21

Forks

Language

Python

License

Apache-2.0

Last pushed

Apr 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tanat05/korcen-kogpt2"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.