dongyuanxin/news-emotion
๐ ้่ๆๆฌๆ ๆๅๆๆจกๅ
ArchivedCombines multiple Chinese sentiment lexicons (HowNet, NTUSD) with scikit-learn classifiers to classify financial news as positive, negative, or neutral sentiment. Uses word frequency vectorization and ensemble methods with leave-one-out cross-validation for model evaluation. Provides pre-trained logistic regression models alongside retrainable pipelines that handle HTML cleaning, simplified/traditional Chinese conversion, and stopword filtering.
353 stars. No commits in the last 6 months.
Stars
353
Forks
127
Language
Python
License
—
Category
Last pushed
Jun 11, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dongyuanxin/news-emotion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
pouyaardehkhani/FinancialAnalysis
This notebook provides some skills to perform financial analysis on economical data.
icoxfog417/awesome-financial-nlp
Researches for Natural Language Processing for Financial Domain
clonesRpeople2/financial-risk-analyzer
๐ Analyze financial risk for stocks and portfolios with real data from Yahoo Finance to make...
yash6810/Sentilyze
End-to-end stock sentiment analysis & momentum prediction system using NLP (FinBERT) and...
LikithMeruvu/FinBert-Finetuning-for-Stock-Sentiment
I have fineTuned FinBert Model on 4.9k Financial News Headlines, Got 81-82% ACC and it perfrom...