https://github.com/asreview/paper-asreview

Scripts for paper: 'ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews'

https://github.com/asreview/paper-asreview

Science Score: 13.0%

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

  • CITATION.cff file
  • codemeta.json file
  • .zenodo.json file
  • DOI references
    Found 7 DOI reference(s) in README
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (12.9%) to scientific vocabulary

Keywords

asreview paper-asreview
Last synced: 9 months ago · JSON representation

Repository

Scripts for paper: 'ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews'

Basic Info
Statistics
  • Stars: 9
  • Watchers: 4
  • Forks: 3
  • Open Issues: 0
  • Releases: 0
Topics
asreview paper-asreview
Created over 6 years ago · Last pushed over 4 years ago
Metadata Files
Readme License

README.md

Scripts for 'ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews'

This repository contains the scripts of the simulation study found in the paper ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews. This paper introduces the ASReview project and the ASReview LAB software. The results of the simulation study are available via: 10.17605/OSF.IO/2JKD6.

:raised_hand: The scripts in this repository make use of ASReview version 0.7.2. Many improvements were made to the ASReview software afterward. We encourage you to use the latest version for new studies. See the extensive ASReview documentation for all features of ASReview for screening and simulating.

:arrows_counterclockwise: A persistent version of the scripts can be found on Zenodo Ferdinands et al. (2020, September 11). Scripts for 'ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews' (Version v1.0.1). Zenodo. http://doi.org/10.5281/zenodo.4024122.

Installation

Running this simulation study requires Python 3.6+. The results in this repository are generated with ASReview v0.7.2. To run the code in parallel, you also need an implementation of the MPI standard. The most well known standard is OpenMPI (this is not a python package and should be installed separately).

Install the python depencies with pip install -r requirements.txt

Simulation study

This directory contains scripts to reproduce reproduce the results of simulation study for the paper ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews. It consists of three parts:

1) optimizing hyperparameters 2) simulating systematic reviews 3) visualizing the simulation results

The figure in the paper displays the performance of an Automated Systematic Review model (Naive Bayes + TF-IDF + Certainty + Dynamic Supersampling) over 15 runs on four already labeled datasets. See paper for details on the datasets.

The simulation output is available on the Open Science Framework.

License

The scripts in this repository are MIT licensed.

Contact

Questions or remarks? Please send an email to asreview@uu.nl.

Owner

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

ASReview - Active learning for Systematic Reviews

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Dependencies

requirements.txt pypi
  • asreview ==0.7.2
  • asreview-hyperopt *
  • asreview-visualization *
  • mpi4py *