linguishi/chinese_sentiment resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1086 stars · 124 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A Chinese sentiment analysis project implementing text classification with CNN and BI-LSTM models in TensorFlow. It includes data preparation scripts, pretrained Chinese word vector integration, and training/evaluation pipelines achieving roughly 90% accuracy on a hotel review corpus.

Use cases

• classify chinese reviews as positive or negative
• train a cnn text classifier on chinese corpus
• train a bi-lstm sentiment model
• learn chinese sentiment analysis with tensorflow
• run text classification with pretrained chinese word vectors
• segment chinese text with jieba for classification

When to choose

• you need a reference implementation of CNN or BI-LSTM for Chinese text classification
• you want to learn end-to-end Chinese NLP pipelines including tokenization, embeddings, and training
• you have a small labeled Chinese corpus in the expected format and want a quick baseline

When to avoid

• you need production-ready sentiment analysis with modern transformer models
• you require a maintained library with a stable API or license
• you work outside Python 3.6 / TensorFlow 1.x environments
• you need multilingual or non-Chinese sentiment analysis

Facets

learning-resource · maturity maintenance

nlp machine-learning deep-learning machine-learning deep-learning python sentiment-analysis text-classification cnn bilstm chinese-nlp tensorflow word-embeddings jieba natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="linguishi/chinese_sentiment")