Scripts for a simulation on the effect of dataset size on neural network performance for active learning applied to systematic reviewing

Govert Verberg, Jonathan de Bruin, R. van de Schoot, Laura Hofstee, Ayoub Bagheri

Research output: Non-textual formSoftwareAcademic

Abstract

It is generally assumed that having more data available will lead to increased performance when using machine learning. This assumption was tested in a specific problem setting: using neural networks in combination with active learning to aid in systematic reviewing. This repository contains the scripts for performing a simulation study using the neural network clasifier as implemented in ASReview. The simulation mode was applied to different sized samples out of three different datasets, to measure the change in performance.
Original languageEnglish
PublisherZenodo
DOIs
Publication statusPublished - 2021

Keywords

  • machine learning active learning ASReview KEYWORD

Fingerprint

Dive into the research topics of 'Scripts for a simulation on the effect of dataset size on neural network performance for active learning applied to systematic reviewing'. Together they form a unique fingerprint.

Cite this