# yao8839836/text_gcn

Graph Convolutional Networks for Text Classification. AAAI 2019

Repository: https://github.com/yao8839836/text_gcn
Canonical: https://ross.abutalabs.com/products/text_gcn
Language: Python
License Family: other
Topics: deep-learning, nlp, text-classification, graph-convolutional-networks
Last push: 2021-12-29T03:25:22+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2914, "days_push": 1708, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1389, forks 438 (observed 2026-08-28T04:04:35.409134+00:00)

## What it is
The official implementation of Text GCN, a Graph Convolutional Network approach for text classification published at AAAI 2019. It builds word-document graphs from corpora and trains a GCN to classify documents on standard benchmarks like 20NG, R8, R52, Ohsumed, and MR.

## Use cases
- classify documents into categories using graph neural networks
- reproduce Text GCN results from the AAAI 2019 paper
- run text classification on benchmark datasets like 20 Newsgroups
- build word-document graphs from a text corpus
- experiment with GCNs for NLP tasks
- compare graph-based text classification against baselines

## When to choose
- you want to reproduce or build on the Text GCN paper's approach
- you need graph-based document classification on small-to-medium benchmark corpora
- you are researching graph neural networks for NLP

## When to avoid
- you need a production-ready, maintained text classification pipeline
- you want modern TensorFlow 2.x or PyTorch support
- you need inductive classification on unseen documents (use fast_text_gcn instead)
- you require a permissive license for commercial use

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: graph-convolutional-networks, text-classification, tensorflow, research-code, aaai-2019, natural-language-processing

## Member repositories
- yao8839836/text_gcn (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:35.409134+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:44.522248+00:00, confidence not recorded.
  - readme: https://github.com/yao8839836/text_gcn (fetched 2026-08-28T04:04:35.409134+00:00, sha 162f337cac90)
- Data as of 2026-08-30T08:39:29.467469+00:00.