Beomi/KcBERT

πŸ€— Pretrained BERT model & WordPiece tokenizer trained on Korean Comments ν•œκ΅­μ–΄ λŒ“κΈ€λ‘œ ν”„λ¦¬νŠΈλ ˆμ΄λ‹ν•œ BERT λͺ¨λΈκ³Ό 데이터셋

42
/ 100
Emerging

This project offers specialized AI models designed to understand casual, informal Korean text, particularly online comments. It takes raw Korean user-generated content, like social media comments, and processes it to extract meaning, sentiment, or other insights. This is ideal for market researchers, social media analysts, or customer service managers who need to analyze public opinion and feedback expressed in everyday Korean.

495 stars. No commits in the last 6 months.

Use this if you need to analyze large volumes of Korean online comments, forum posts, or social media discussions to understand sentiment, identify key topics, or categorize user feedback, where standard models struggle with slang, typos, and informal language.

Not ideal if your primary data source consists of formal Korean documents like news articles, academic papers, or official reports, as other models trained on such refined text might be more suitable.

social-media-analysis korean-language-processing sentiment-analysis customer-feedback market-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

495

Forks

45

Language

License

MIT

Last pushed

Nov 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Beomi/KcBERT"

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