Data

Tools

Indexes

Applications

Experiments

Open Source Science

asreview

Active learning for systematic reviews

https://github.com/asreview/asreview

Science Score: 57.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ✓
    DOI references
    Found 6 DOI reference(s) in README
  • ○
    Academic publication links
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.5%) to scientific vocabulary

Keywords

active-learning asreview deep-learning language-model learning-algorithms literature llm natural-language-processing neural-network research systematic-literature-reviews systematic-reviews utrecht-university

Keywords from Contributors

plots fairness energy-system actions distribution discovery rdm sf agents workshop
Last synced: 6 months ago · JSON representation ·

Repository

Active learning for systematic reviews

Basic Info
  • Host: GitHub
  • Owner: asreview
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Homepage: https://asreview.ai
  • Size: 160 MB
Statistics
  • Stars: 768
  • Watchers: 21
  • Forks: 146
  • Open Issues: 66
  • Releases: 141
Topics
active-learning asreview deep-learning language-model learning-algorithms literature llm natural-language-processing neural-network research systematic-literature-reviews systematic-reviews utrecht-university
Created about 7 years ago · Last pushed 6 months ago
Metadata Files
Readme Contributing License Citation Security

README.md


🎉 ASReview LAB v2 is here! 🎉
Faster, smarter, and more flexible than ever before.
Discover the new AI models, improved workflow, and enhanced user experience.



ASReview LAB: Active Learning for Systematic Reviews

ASReview LAB is an open-source machine learning tool for efficient, transparent, and interactive screening of large textual datasets. It is widely used for systematic reviews, meta-analyses, and any scenario requiring systematic text screening.

The key features of ASReview LAB are:

  • Active Learning: Interactively prioritize records using AI models that learn from your labeling decisions.
  • Scientifically validated: ASReview LAB has been scientifically validated and published in Nature Machine Intelligence.
  • Flexible AI Models: Choose from pre-configured ELAS models or build your own with custom components.
  • Simulation toolkit: Assess model performance on fully labeled datasets.
  • Label Management: All decisions are saved automatically; easily change labels at any time.
  • User-Centric Design: Humans are the oracle; the interface is transparent and customizable.
  • Privacy First: Everything is open source and no usage or user data is collected.

What's New in Version 2?

On May 14th, ASReview LAB version 2 was released with a large set of new features. The most notable new features are:

  • New ELAS AI Models: Pre-configured, high-performance (+24%) models for different use cases (Ultra, Multilingual, Heavy). More new and exciting models can now be found in our new ASReview Dory extension.
  • Improved User Experience: The interface is faster, progress monitoring is better, and there are more customization options (such as dark mode, font size, and keyboard shortcuts).
  • ASReview LAB Server with crowd screening: Screen a single project with multiple experts. All users interact with the same AI model.
  • Quick project setup: Start screening new datasets in seconds using the quick setup for projects.
  • Add customizable tags: Add tags and groups of tags to your records and label decisions. This makes data extraction much easier!
  • Improved simulation API: The new and flexible simulation API opens up a whole new simulation potential. It is a perfect tool for hunting for even better-performing models.

Installation

Requires Python 3.10 or later.

bash pip install asreview

Upgrade:

bash pip install --upgrade asreview

For Docker and advanced installation, see the installation guide.

Latest version of ASReview LAB: PyPI version

The ASReview LAB Workflow

  1. Import Data: Load your dataset (CSV, RIS, XLSX, etc.).
  2. Create Project: Set up a new review or simulation project.
  3. Select Prior Knowledge: Optionally provide records you already know are relevant or not relevant.
  4. Start Screening: Label records as Relevant or Not Relevant; the AI model continuously improves.
  5. Monitor Progress: Use the dashboard to track your progress and decide when to stop.
  6. Export Results: Download your labeled dataset or project file.

ASReview LAB

Documentation & Resources

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 you need.

For more scientific publications on the ASReview software, go to asreview.ai/papers.

Community & Contact

The best resources to find an answer to your question or ways to get in contact with the team are:

License

The ASReview software has an Apache 2.0 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.

Owner

  • Name: ASReview
  • Login: asreview
  • Kind: organization
  • Email: asreview@uu.nl
  • Location: Utrecht University

ASReview - Active learning for Systematic Reviews

Citation (CITATION.cff) 

cff-version: 1.2.0
title: ASReview LAB - A tool for AI-assisted systematic reviews
message: >-
  If you use the ASReview software in your work, please cite it as indicated.
  For referencing the underlying methodology, cite Van de Schoot et
  al. (2021 - https://doi.org/10.1038/s42256-020-00287-7).

type: software
authors:
  - given-names: ASReview LAB developers
    affiliation: Utrecht University
    email: asreview@uu.nl
identifiers:
  - type: doi
    value: 10.1038/s42256-020-00287-7
    description: >-
      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).
repository-code: "https://github.com/asreview/asreview"
url: "https://asreview.ai"
repository-artifact: "https://pypi.org/project/asreview/"
abstract: >-
  The Active learning for Systematic Reviews (ASReview)
  project implements learning algorithms that interactively
  query the researcher. This way of interactive training is
  known as Active Learning. ASReview offers support for
  classical learning algorithms and state-of-the-art
  learning algorithms like neural networks. ASReview LAB is
  the graphical user interface of the open-source research
  software and ships with an Oracle, Exploration, and
  Simulation Mode.
keywords:
  - systematic review
  - prisma
  - active learning
  - statistics
  - machine learning
  - text data
  - natural language processing
  - human-in-the-loop
license: Apache-2.0

GitHub Events

Total
  • Create event: 56
  • Release event: 33
  • Issues event: 110
  • Watch event: 124
  • Delete event: 21
  • Issue comment event: 223
  • Push event: 282
  • Pull request event: 461
  • Pull request review event: 190
  • Pull request review comment event: 143
  • Fork event: 20
Last Year
  • Create event: 56
  • Release event: 33
  • Issues event: 110
  • Watch event: 124
  • Delete event: 21
  • Issue comment event: 223
  • Push event: 282
  • Pull request event: 461
  • Pull request review event: 190
  • Pull request review comment event: 143
  • Fork event: 20

Committers

Last synced: over 2 years ago

All Time
  • Total Commits: 1,149
  • Total Committers: 46
  • Avg Commits per committer: 24.978
  • Development Distribution Score (DDS): 0.522
Past Year
  • Commits: 108
  • Committers: 17
  • Avg Commits per committer: 6.353
  • Development Distribution Score (DDS): 0.454
Top Committers
Name Email Commits
Jonathan de Bruin j****s@g****m 549
Yongchao Terry Ma t****c@g****m 206
qubixes 4****s 89
Rens van de schoot 3****t 58
Raoul Schram r****m@u****l 54
GerbrichFerdinands 4****s 22
Jelle j****a@g****m 22
PeterLombaers 7****s 20
dependabot[bot] 4****] 19
Sofie vd Brand 6****d 11
cskaandorp c****r@c****l 10
Gijs Mourits g****8@h****m 10
Jonathan de Bruin j****e@g****m 10
Jelle Teijema j****a@u****l 6
Otto Mättas o****s@g****m 6
Sasafrass a****a@g****m 4
Leonardo Vida l****a@g****m 4
govertv 4****v 4
Andrew Rodwin a****n@m****m 3
P.Zahedi p****i@g****m 3
Abel Soares Siqueira a****a@g****m 3
Rohit Garud r****2@g****m 3
Carsten Behring c****g@g****m 3
Mathieu Rietman m****n@h****m 2
Duco Veen d****n@g****m 2
Yifei Michelle Liu m****e@g****m 2
Roy van Elk g****b@r****l 2
Jurriaan H. Spaaks j****s@e****l 2
jelletreep 4****p 2
lastoel 7****l 2
and 16 more...
Committer Domains (Top 20 + Academic)
uu.nl: 2 applike.nl: 1 dans.knaw.nl: 1 pm.me: 1 esciencecenter.nl: 1 royvanelk.nl: 1 medbaye.com: 1 compunist.nl: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time
  • Total issues: 187
  • Total pull requests: 474
  • Average time to close issues: 9 months
  • Average time to close pull requests: 12 days
  • Total issue authors: 85
  • Total pull request authors: 34
  • Average comments per issue: 2.06
  • Average comments per pull request: 0.77
  • Merged pull requests: 383
  • Bot issues: 0
  • Bot pull requests: 32
Past Year
  • Issues: 54
  • Pull requests: 190
  • Average time to close issues: about 1 month
  • Average time to close pull requests: 4 days
  • Issue authors: 30
  • Pull request authors: 16
  • Average comments per issue: 0.39
  • Average comments per pull request: 0.27
  • Merged pull requests: 140
  • Bot issues: 0
  • Bot pull requests: 13
View more stats
Top Authors
Issue Authors
  • J535D165 (29)
  • jspaaks (28)
  • Rensvandeschoot (15)
  • PeterLombaers (8)
  • jteijema (8)
  • george-gca (6)
  • timovdk (5)
  • abelsiqueira (4)
  • taleevenhuis (4)
  • terrymyc (3)
  • fqixiang (3)
  • jf29medma (2)
  • wolfgangmeisen (2)
  • SamyAteia (2)
  • j0sien (2)
Pull Request Authors
  • J535D165 (348)
  • cskaandorp (77)
  • Rensvandeschoot (52)
  • dependabot[bot] (41)
  • PeterLombaers (34)
  • BerkeYazan (31)
  • pre-commit-ci[bot] (15)
  • jteijema (14)
  • timovdk (11)
  • jspaaks (6)
  • terrymyc (6)
  • dometto (5)
  • abelsiqueira (4)
  • laurens88 (4)
  • rohitgarud (4)
Top Labels
Issue Labels
bug (82) enhancement (35) help wanted (24) good first issue (14) Discussion (14) front-end (13) documentation (7) dependencies (5) CI (5) question (2) extensions (2) models (2) stale (1) simulation (1)
Pull Request Labels
enhancement (49) dependencies (43) javascript (36) documentation (24) front-end (23) bug (20) CI (3) Discussion (2) extensions (1) stale (1) simulation (1) Docker (1) good first issue (1) models (1)

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 5,731 last-month
  • Total docker downloads: 47
  • Total dependent packages: 6
  • Total dependent repositories: 21
  • Total versions: 146
  • Total maintainers: 2
pypi.org: asreview

ASReview LAB - A tool for AI-assisted systematic reviews

  • Versions: 146
  • Dependent Packages: 6
  • Dependent Repositories: 21
  • Downloads: 5,731 Last month
  • Docker Downloads: 47
Rankings
Dependent packages count: 1.6%
Stargazers count: 2.8%
Average: 3.0%
Docker downloads count: 3.1%
Dependent repos count: 3.2%
Downloads: 3.2%
Forks count: 4.4%
Maintainers (2)
j535d165 rensvandeschoot
Last synced: 6 months ago