# brightmart/text_classification

all kinds of text classification models and more with deep learning

Repository: https://github.com/brightmart/text_classification
Canonical: https://ross.abutalabs.com/products/text_classification
Language: Python
License: MIT
License Family: permissive
Topics: classification, nlp, fasttext, textcnn, textrnn, tensorflow, multi-label, multi-class, attention-mechanism, text-classification, convolutional-neural-networks, sentence-classification, memory-networks
Last push: 2023-09-28T05:55:11+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": 3382, "days_push": 1070, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7940, forks 2532 (observed 2026-08-28T04:10:10.030079+00:00)

## What it is
A collection of deep learning baseline models for text classification in NLP, implemented in TensorFlow. It covers classic architectures like FastText, TextCNN, TextRNN, seq2seq with attention, and memory networks, with support for multi-label and multi-class classification.

## Use cases
- classify text documents into categories with deep learning
- train a multi-label text classification model
- get baseline models for sentence classification
- compare classic text classification architectures like TextCNN and FastText
- build a sentiment or topic classifier in TensorFlow
- experiment with memory networks for NLP tasks

## When to choose
- you need classic baseline models for text classification research or prototyping
- you want TensorFlow implementations of TextCNN, TextRNN, FastText, or memory networks
- you need multi-label classification support with reference implementations

## When to avoid
- you need state-of-the-art transformer-based classifiers like BERT fine-tuning
- you want a production-ready, actively maintained NLP framework
- you prefer PyTorch or modern LLM-based approaches

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, deep-learning
- domain: machine-learning, deep-learning
- platform: python
- tags: text-classification, fasttext, textcnn, textrnn, multi-label-classification, tensorflow, attention-mechanism, memory-networks, baseline-models, natural-language-processing

## Member repositories
- brightmart/text_classification (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:10.030079+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 2026-08-29T17:33:13.942586+00:00, confidence not recorded.
  - readme: https://github.com/brightmart/text_classification (fetched 2026-08-28T04:10:10.030079+00:00, sha 8893a68ce237)
- Data as of 2026-08-30T08:39:29.467469+00:00.