Hanszhuang/yunyi

2018“云移杯- 景区口碑评价分值预测

34
/ 100
Emerging

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.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

30

Forks

17

Language

Jupyter Notebook

License

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.