<p align="center">
<a href="https://github.com/asreview/asreview">
<img width="60%" height="60%" src="https://raw.githubusercontent.com/asreview/asreview-artwork/master/LogoASReview/SVG/GitHub_Repo_Card_Transparent.svg">
</a>
</p>
## ASReview: Active learning for Systematic Reviews
[](https://badge.fury.io/py/asreview) [](https://asreview.readthedocs.io/en/latest/?badge=latest) [](https://zenodo.org/badge/latestdoi/164874894)
[](https://github.com/asreview/asreview#installation) [](https://bestpractices.coreinfrastructure.org/projects/4755)
Systematically screening large amounts of textual data is time-consuming and
often tiresome. The rapidly evolving field of Artificial Intelligence (AI) has
allowed the development of AI-aided pipelines that assist in finding relevant
texts for search tasks. A well-established approach to increasing efficiency
is screening prioritization via [Active
Learning](https://asreview.readthedocs.io/en/latest/guides/activelearning.html).
The Active learning for Systematic Reviews (ASReview) project, published in
[*Nature Machine Intelligence*](https://doi.org/10.1038/s42256-020-00287-7)
implements different machine learning algorithms that interactively query the
researcher. ASReview LAB is designed to accelerate the step of screening
textual data with a minimum of records to be read by a human with no or very
few false negatives. ASReview LAB will save time, increase the quality of
output and strengthen the transparency of work when screening large amounts of
textual data to retrieve relevant information. Active Learning will support
decision-making in any discipline or industry.
ASReview software implements three different modes:
- **Oracle** Screen textual data in
interaction with the active learning model. The reviewer is the 'oracle',
making the labeling decisions.
- **Exploration** Explore or
demonstrate ASReview LAB with a completely labeled dataset. This mode is
suitable for teaching purposes.
- **Simulation** Evaluate
the performance of active learning models on fully labeled data. Simulations
can be run in ASReview LAB or via the command line interface with more
advanced options.
## Installation
The ASReview software requires Python 3.8 or later. Detailed step-by-step
instructions to install Python and ASReview are available for
[Windows](https://asreview.ai/installation-guide-windows/) and
[macOS](https://asreview.ai/installation-guide-macos/) users.
```bash
pip install asreview
```
Upgrade ASReview with the following command:
```bash
pip install --upgrade asreview
```
To install ASReview LAB with Docker, see [Install with Docker](https://asreview.readthedocs.io/en/latest/installation.html).
## How it works
[](https://www.youtube.com/watch?v=k-a2SCq-LtA)
## Getting started
[Getting Started with ASReview
LAB](https://asreview.readthedocs.io/en/latest/about.html).
[](https://asreview.readthedocs.io/en/latest/lab/overview_lab.html "ASReview LAB")
## Citation
If you wish to cite the underlying methodology of the ASReview software,
please use the following publication in Nature Machine Intelligence:
> van de Schoot, R., de Bruin, J., Schram, R. et al. An open source machine
learning framework for efficient and transparent systematic reviews.
Nat Mach Intell 3, 125–133 (2021). https://doi.org/10.1038/s42256-020-00287-7
For citing the software, please refer to the specific release of
the ASReview software on Zenodo https://doi.org/10.5281/zenodo.3345592. The menu on the
right can be used to find the citation format of prevalence.
For more scientific publications on the ASReview software, go to
[asreview.ai/papers](https://asreview.ai/papers/).
## Contact
For an overview of the team working on ASReview, see [ASReview Research Team](https://asreview.ai/about).
ASReview LAB is maintained by
[Jonathan de Bruin](https://github.com/J535D165) and [Yongchao Terry Ma](https://github.com/terrymyc).
The best resources to find an answer to your question or ways to get in
contact with the team are:
- Documentation - [asreview.readthedocs.io](https://asreview.readthedocs.io/)
- Newsletter - [asreview.ai/newsletter/subscribe](https://asreview.ai/newsletter/subscribe)
- Quick tour - [ASReview LAB quick tour](https://asreview.readthedocs.io/en/latest/lab/overview_lab.html)
- Issues or feature requests - [ASReview issue tracker](https://github.com/asreview/asreview/issues)
- FAQ - [ASReview Discussions](https://github.com/asreview/asreview/discussions?discussions_q=sort%3Atop)
- Donation - [asreview.ai/donate](https://asreview.ai/donate)
- Contact - [asreview@uu.nl](mailto:asreview@uu.nl)
## License
The ASReview software has an Apache 2.0 [LICENSE](LICENSE). The ASReview team
accepts no responsibility or liability for the use of the ASReview tool or any
direct or indirect damages arising out of the application of the tool.
Raw data
{
"_id": null,
"home_page": "https://github.com/asreview/asreview",
"name": "asreview",
"maintainer": null,
"docs_url": null,
"requires_python": "~=3.8",
"maintainer_email": null,
"keywords": "systematic review, machine-learning",
"author": "ASReview LAB developers",
"author_email": "asreview@uu.nl",
"download_url": "https://files.pythonhosted.org/packages/de/4e/766da7890d55b6dec623150e465b998fd8ee8daf2bbdbe2c0932e695119b/asreview-1.6.3.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n <a href=\"https://github.com/asreview/asreview\">\n <img width=\"60%\" height=\"60%\" src=\"https://raw.githubusercontent.com/asreview/asreview-artwork/master/LogoASReview/SVG/GitHub_Repo_Card_Transparent.svg\">\n </a>\n</p>\n\n## ASReview: Active learning for Systematic Reviews\n\n[](https://badge.fury.io/py/asreview) [](https://asreview.readthedocs.io/en/latest/?badge=latest) [](https://zenodo.org/badge/latestdoi/164874894)\n [](https://github.com/asreview/asreview#installation) [](https://bestpractices.coreinfrastructure.org/projects/4755)\n\nSystematically screening large amounts of textual data is time-consuming and\noften tiresome. The rapidly evolving field of Artificial Intelligence (AI) has\nallowed the development of AI-aided pipelines that assist in finding relevant\ntexts for search tasks. A well-established approach to increasing efficiency\nis screening prioritization via [Active\nLearning](https://asreview.readthedocs.io/en/latest/guides/activelearning.html).\n\nThe Active learning for Systematic Reviews (ASReview) project, published in\n[*Nature Machine Intelligence*](https://doi.org/10.1038/s42256-020-00287-7)\nimplements different machine learning algorithms that interactively query the\nresearcher. ASReview LAB is designed to accelerate the step of screening\ntextual data with a minimum of records to be read by a human with no or very\nfew false negatives. ASReview LAB will save time, increase the quality of\noutput and strengthen the transparency of work when screening large amounts of\ntextual data to retrieve relevant information. Active Learning will support \ndecision-making in any discipline or industry.\n\nASReview software implements three different modes:\n\n- **Oracle** Screen textual data in\n interaction with the active learning model. The reviewer is the 'oracle',\n making the labeling decisions.\n- **Exploration** Explore or\n demonstrate ASReview LAB with a completely labeled dataset. This mode is\n suitable for teaching purposes.\n- **Simulation** Evaluate\n the performance of active learning models on fully labeled data. Simulations\n can be run in ASReview LAB or via the command line interface with more\n advanced options.\n\n\n## Installation\n\nThe ASReview software requires Python 3.8 or later. Detailed step-by-step\ninstructions to install Python and ASReview are available for\n[Windows](https://asreview.ai/installation-guide-windows/) and\n[macOS](https://asreview.ai/installation-guide-macos/) users.\n\n```bash\npip install asreview\n```\n\nUpgrade ASReview with the following command:\n\n```bash\npip install --upgrade asreview\n```\n\nTo install ASReview LAB with Docker, see [Install with Docker](https://asreview.readthedocs.io/en/latest/installation.html).\n\n## How it works\n\n[](https://www.youtube.com/watch?v=k-a2SCq-LtA)\n\n\n## Getting started\n\n[Getting Started with ASReview\nLAB](https://asreview.readthedocs.io/en/latest/about.html).\n\n[](https://asreview.readthedocs.io/en/latest/lab/overview_lab.html \"ASReview LAB\")\n\n## Citation\n\nIf you wish to cite the underlying methodology of the ASReview software,\nplease use the following publication in Nature Machine Intelligence:\n\n> van de Schoot, R., de Bruin, J., Schram, R. et al. An open source machine\n learning framework for efficient and transparent systematic reviews.\n Nat Mach Intell 3, 125\u2013133 (2021). https://doi.org/10.1038/s42256-020-00287-7\n\nFor citing the software, please refer to the specific release of\nthe ASReview software on Zenodo https://doi.org/10.5281/zenodo.3345592. The menu on the\nright can be used to find the citation format of prevalence.\n\nFor more scientific publications on the ASReview software, go to\n[asreview.ai/papers](https://asreview.ai/papers/).\n\n## Contact\n\nFor an overview of the team working on ASReview, see [ASReview Research Team](https://asreview.ai/about).\nASReview LAB is maintained by\n[Jonathan de Bruin](https://github.com/J535D165) and [Yongchao Terry Ma](https://github.com/terrymyc).\n\nThe best resources to find an answer to your question or ways to get in\ncontact with the team are:\n\n- Documentation - [asreview.readthedocs.io](https://asreview.readthedocs.io/)\n- Newsletter - [asreview.ai/newsletter/subscribe](https://asreview.ai/newsletter/subscribe)\n- Quick tour - [ASReview LAB quick tour](https://asreview.readthedocs.io/en/latest/lab/overview_lab.html)\n- Issues or feature requests - [ASReview issue tracker](https://github.com/asreview/asreview/issues)\n- FAQ - [ASReview Discussions](https://github.com/asreview/asreview/discussions?discussions_q=sort%3Atop)\n- Donation - [asreview.ai/donate](https://asreview.ai/donate)\n- Contact - [asreview@uu.nl](mailto:asreview@uu.nl)\n\n## License\n\nThe ASReview software has an Apache 2.0 [LICENSE](LICENSE). The ASReview team\naccepts no responsibility or liability for the use of the ASReview tool or any\ndirect or indirect damages arising out of the application of the tool.\n",
"bugtrack_url": null,
"license": null,
"summary": "ASReview LAB - A tool for AI-assisted systematic reviews",
"version": "1.6.3",
"project_urls": {
"Bug Reports": "https://github.com/asreview/asreview/issues",
"Homepage": "https://github.com/asreview/asreview",
"Source": "https://github.com/asreview/asreview/"
},
"split_keywords": [
"systematic review",
" machine-learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "40b647918bf611aeb17b87e0c91f3d40346326bf343a0488a38a73d0db938de1",
"md5": "71214b89c3428a9b1f07c352f095116b",
"sha256": "2e48cc47f96df0fbbce5120935692279453922534adefbbbb502c50384218783"
},
"downloads": -1,
"filename": "asreview-1.6.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "71214b89c3428a9b1f07c352f095116b",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "~=3.8",
"size": 3504141,
"upload_time": "2024-09-02T14:43:18",
"upload_time_iso_8601": "2024-09-02T14:43:18.593239Z",
"url": "https://files.pythonhosted.org/packages/40/b6/47918bf611aeb17b87e0c91f3d40346326bf343a0488a38a73d0db938de1/asreview-1.6.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "de4e766da7890d55b6dec623150e465b998fd8ee8daf2bbdbe2c0932e695119b",
"md5": "d40cac8a3c57498cba785250f6d2105e",
"sha256": "f3b8f538cf1d91c571dc960d01e5a15a16455131d23f4c9f26e250ba09ba334e"
},
"downloads": -1,
"filename": "asreview-1.6.3.tar.gz",
"has_sig": false,
"md5_digest": "d40cac8a3c57498cba785250f6d2105e",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "~=3.8",
"size": 3404948,
"upload_time": "2024-09-02T14:43:20",
"upload_time_iso_8601": "2024-09-02T14:43:20.604354Z",
"url": "https://files.pythonhosted.org/packages/de/4e/766da7890d55b6dec623150e465b998fd8ee8daf2bbdbe2c0932e695119b/asreview-1.6.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-09-02 14:43:20",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "asreview",
"github_project": "asreview",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "asreview"
}
JSON
