Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Active Learning for Text Classification in Python
| Date | Stars |
|---|---|
| 2026-07-24 | 646 |
| 2026-07-25 | 646 |
| 2026-07-28 | 646 |
| 2026-07-30 | 646 |
| 2026-08-06 | 646 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://pypi.org/project/small-text/)
[](https://anaconda.org/conda-forge/small-text)
[](https://codecov.io/gh/webis-de/small-text)
[](https://small-text.readthedocs.io/en/v2.0.0.dev4/)
[](CONTRIBUTING.md)
[](LICENSE)
[](https://zenodo.org/records/20358671)
<p align="center">
<img width="450" src="https://github.com/webis-de/small-text/blob/dev/docs/_static/small-text-logo.png?raw=true" alt="small-text logo" />
</p>
> Active Learning for Text Classification in Python.
<hr>
[Installation](#installation) | [Quick Start](#quick-start) | [Contribution](CONTRIBUTING.md) | [Changelog][changelog] | [**Docs**][documentation_main]
Small-Text provides state-of-the-art **Active Learning** for Text Classification.
Several pre-implemented query strategies, initialization strategies, and stopping criteria are provided,
which can be easily mixed and matched to build active learning experiments or applications.
## What is Active Learning?
[Active learning](https://small-text.readthedocs.io/en/latest/active_learning.html) allows you to efficiently label training data for supervised learning when you have little to no labeled data.
<p align="center">
<img src="https://raw.githubusercontent.com/webis-de/small-text/dev/docs/_static/learning-curve-example.gif?raw=true" alt="Learning curve example for the TREC-6 dataset." width="60%">
</p>
## Active Learning in Practice
Active Learning for Text Classification has been applied across diverse fields, including biomedical research, social science, information science, computer science, and political communication:
- [Bootstrapping a biomedical corpus of digenic variant combinations](https://pubmed.ncbi.nlm.nih.gov/38805753/)
- [Detecting disclosures of individuals' employment status on social media](https://aclanthology.org/2022.acl-long.453/)
- [Accelerating systematic literature reviews](https://www.nature.com/articles/s42256-020-00287-7)
- [Topic categorization of citizen contributions](https://link.springer.com/chapter/10.1007/978-3-031-15086-9_24)
- [Classifying Speech Acts in Political Communication](http://doi.org/10.15439/2023F3485)
See [the showcase section][documentation_showcase] specifically for previous active learning applications where small-text was used.
## Features
- Provides unified interfaces for Active Learning, allowing you to
easily mix and match query strategies with classifiers provided by [sklearn](https://scikit-learn.org/), [PyTorch](https://pytorch.org/), or [transformers](https://github.com/huggingface/transformers).
- Supports GPU-based [Pytorch](https://pytorch.org/) models and integrates [transformers](https://github.com/huggingface/transformers)
so that you can use state-of-the-art Text Classification models for Active Learning.
- GPU is supported but not required. CPU-only use cases require only
a lightweight installation with minimal dependencies.
- Multiple scientifically evaluated components are pre-implemented and ready to use (Query Strategies, Initialization Strategies, and Stopping Criteria).
---
## News
**Version 2.0.0 dev4** ([v2.0.0.dev4][changelog_2.0.0dev4]) - May 23rd, 2026
- This is a development release with the most changes so far. You can consider it an alpha release, which does not guarantee you stable interfaces yet,
but is otherwise ready to use.
- Version 2.0.0 offers refined interExcerpt of 13,365 characters
Read on GitHub
Christopher Schröder · Germany
792
5
2
2
1
1
1
Raphael Mitsch · @climatiq · Austria
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:f372d520f0841b7a, topic:nlp, topic:natural-language-processing, topic:text-classification
matched fp:f372d520f0841b7a, topic:deep-learning, topic:pytorch