Hanszhuang/yunyi
2018“云移杯- 景区口碑评价分值预测
Implements CNN and RNN architectures for Chinese scenic spot review sentiment scoring, leveraging Keras with TensorFlow-GPU backend and jieba for Chinese text tokenization. The solution combines multiple neural network approaches (CNN, RNN, hybrid CNN-RNN) with custom stopword filtering to predict numerical reputation scores from user reviews. Training uses early stopping on validation loss with online evaluation reaching ~0.506 accuracy through iterative model refinement and hyperparameter tuning.
No commits in the last 6 months.
Stars
30
Forks
17
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 10, 2018
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/Hanszhuang/yunyi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
msahamed/yelp_comments_classification_nlp
Yelp round-10 review comments classification using deep learning (LSTM and CNN) and natural...
Jetsu0/hospital-reviews-topic-modelling-sentiment-analysis
🎭 Analyze hospital reviews from Google Maps with topic modelling and sentiment analysis to...
glennfang/apple-app-reviews-scraper
Apple App Store reviews scraper with backoff strategy to tackle rate limiting
HarshCasper/Blind-App-Reviews
Scraped reviews of over 25 companies from the Blind App ⚡️
jeffjohannsen/Predicting_Yelp_Review_Quality
[Archived] Classical NLP pipeline (2019-2020) predicting Yelp review quality using TF-IDF,...