monologg/korean-hate-speech-koelectra

Bias, Hate classification with KoELECTRA 👿

40
/ 100
Emerging

This project helps online community managers, content moderators, or social listening analysts identify and filter harmful content in Korean text. You provide Korean comments and titles, and it outputs classifications for whether the text contains bias (gender, other, none) and hate speech (hate, offensive, none). This tool is for anyone responsible for maintaining healthy online discussions or analyzing sentiment in Korean online communities.

No commits in the last 6 months.

Use this if you need to automatically detect and categorize bias and hate speech in Korean comments or user-generated text.

Not ideal if you are looking for a solution that handles languages other than Korean or requires highly nuanced, human-level interpretation of complex conversational dynamics.

content-moderation online-community-management social-listening sentiment-analysis korean-language-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

27

Forks

8

Language

Python

License

CC-BY-SA-4.0

Last pushed

Jun 12, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/monologg/korean-hate-speech-koelectra"

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