asreview 1.0a1

Active learning for Systematic Reviews

ASReview: Active learning for Systematic Reviews

Systematic Reviews are “top of the bill” in research. The number of scientific studies are increasing exponentially in many scholarly fields. Performing a sound systematic review is a time-consuming and sometimes boring task. The ASReview software is designed to accelerate the step of screening abstracts and titles with a minimum of papers to be read by a human with no or very few false negatives.

The Active learning for Systematic Reviews (ASReview) project, publised in Nature Machine Intelligence, implements machine learning algorithms that interactively query the researcher. This way of interactive machine learning is known as Active Learning. ASReview offers support for classical learning algorithms and state-of-the-art learning algorithms like neural networks.

ASReview software implements two different modes:

• ASReview LAB This modus is used to perform a systematic review with interaction by the reviewer (the 'oracle' in literature on active learning). The software presents papers to the reviewer, whereafter the reviewer classifies them. See ASReview LAB.
• Simulate The simulation modus is used to measure the performance of the active learning software on the results of fully labeled systematic reviews. To use the simulation mode, knowledge on programming and bash/Command Prompt is highly recommended.

Want to keep up-to-date with the latest ASReview updates? Sign up for the newsletter 📰

Installation

The ASReview software requires Python 3.7+. Detailed step-by-step instructions to install Python and ASReview are available for Windows and macOS users. The project is available on Pypi. Install the project with (Windows users might have to use the prefix python -m):

pip install asreview

Upgrade ASReview with the following command:

pip install --upgrade asreview

Instructions for usage with Docker are here.

ASReview LAB

ASReview LAB is a user-friendly interface for screening documents and experimentation with AI-aided systematic reviews. Read more about using the software in the Quick Tour.

Citation

The following publication in Nature Machine Intelligence can be used to cite the project.

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.nl/papers.

Contact

ASReview is a research project coordinated by Rens van de Schoot (full professor at the Department of Methodology & Statistics at Utrecht University, The Netherlands), together with ASReview lead engineer Jonathan de Bruin. For an overview of the team working on ASReview, see ASReview Research Team.

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

• Documentation - asreview.readthedocs.io
• Newsletter - asreview.ai/newsletter
• Quick tour - ASReview LAB quick tour
• Issues or feature requests - ASReview issue tracker
• FAQ - ASReview Discussions
• Donation - asreview.nl/donate
• Contact - [e-mail]

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.