THUCNews
THUCTC is an efficient Chinese text classification toolkit from Tsinghua University, using bigram features and LibSVM/LibLinear for high accuracy and speed.
Score
30
User Rating
3.0
Free/Trial Support
Supported
Starting Price
--
Last Updated
Aug 04, 2026
Overview
What is THUCNews?
THUCTC (THU Chinese Text Classification) is a toolkit developed by Tsinghua University's NLP lab for automatic training, evaluation, and classification of custom Chinese text corpora, featuring bigram-based methods and support for LibSVM/LibLinear.
What is THUCNews used for?
Top Features
- Chinese text classification with bigram features
- Support for LibSVM and LibLinear models
- High accuracy and fast testing speed
- Customizable training and evaluation parameters
- Includes THUCNews dataset with 14 categories
How to use THUCNews?
Use Java to run the JAR file with parameters for training, testing, or classification; set paths for categories, training data, and models via command-line or API calls in code.
Alternative Tools
No alternative tools found
Pros & Cons
Pros
- High accuracy (up to 88.6% on THUCNews)
- Fast performance
- No dependency on Chinese word segmentation tools
- Free and open-source for non-commercial use
- Comprehensive documentation and examples
Cons
- Primarily designed for Chinese text, less optimal for English
- Memory-intensive for large datasets
- Limited to Java-based deployment
- No built-in GUI, command-line only
Use Cases
- Academic research in NLP
- News categorization for media companies
- Text analysis in education and technology sectors
- Custom classification projects for businesses
THUCNews Pricing
Free Plan
No detailed pricing information available
User Reviews
3.0
out of 5
3.0
No reviews yet
Be the first to review this tool!