yuzhimanhua/MotifClass

MotifClass: Weakly Supervised Text Classification with Higher-order Metadata Information (WSDM'22)

21
/ 100
Experimental

This tool helps researchers and content analysts automatically categorize large collections of documents, even when only a few examples of each category are available. It takes in document text along with associated metadata like authors, venues, or product information, and outputs a classification for each document. This is ideal for academics managing research papers or businesses categorizing product reviews.

No commits in the last 6 months.

Use this if you need to classify documents into categories, but have limited pre-labeled examples and rich metadata associated with your documents.

Not ideal if your documents lack rich metadata or if you have a large dataset of already hand-labeled examples for training.

academic-research content-categorization publication-analysis e-commerce-analytics document-management
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

13

Forks

Language

Python

License

Apache-2.0

Last pushed

Apr 02, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/yuzhimanhua/MotifClass"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.