Performance of active learning models for screening prioritization in systematic reviews: a simulation study into the Average Time to Discover relevant records.

Journal: Systematic reviews
Published Date: Jun 20, 2023

Abstract

BACKGROUND: Conducting a systematic review demands a significant amount of effort in screening titles and abstracts. To accelerate this process, various tools that utilize active learning have been proposed. These tools allow the reviewer to interact with machine learning software to identify relevant publications as early as possible. The goal of this study is to gain a comprehensive understanding of active learning models for reducing the workload in systematic reviews through a simulation study.

Authors

  • Gerbrich Ferdinands
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, Netherlands. gerbrichferdinands@gmail.com.
  • Raoul Schram
    Department of Research and Data Management Services, Information Technology Services, Utrecht University, Utrecht, The Netherlands.
  • Jonathan de Bruin
    Department of Research and Data Management Services, Information Technology Services, Utrecht University, Utrecht, The Netherlands.
  • Ayoub Bagheri
    Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, Netherlands.
  • Daniel L Oberski
    Department of Methodology and Statistics, Faculty of Social Sciences, Utrecht University, Utrecht, Netherlands.
  • Lars Tummers
    School of Governance, Faculty of Law, Economics and Governance, Utrecht University, Utrecht, The Netherlands.
  • Jelle Jasper Teijema
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, Netherlands.
  • Rens van de Schoot
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals