The hardware and bandwidth for this mirror is donated by METANET, the Webhosting and Full Service-Cloud Provider.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]metanet.ch.
Provides functions to conduct title and abstract screening in systematic reviews using large language models, such as the Generative Pre-trained Transformer (GPT) models from 'OpenAI' <https://platform.openai.com/>. These functions can enhance the quality of title and abstract screenings while reducing the total screening time significantly. In addition, the package includes tools for quality assessment of title and abstract screenings, as described in Vembye, Christensen, Mølgaard, and Schytt (2024) <doi:10.31219/osf.io/yrhzm>.
Version: | 0.1.0 |
Depends: | R (≥ 4.1.0) |
Imports: | dplyr, tibble, httr2, stringr, furrr, tidyr, tictoc, askpass, curl, purrr, lifecycle, jsonlite |
Suggests: | future, knitr, rmarkdown, usethis, testthat (≥ 3.0.0) |
Published: | 2024-11-08 |
DOI: | 10.32614/CRAN.package.AIscreenR |
Author: | Mikkel H. Vembye [aut, cre, cph] |
Maintainer: | Mikkel H. Vembye <mikkel.vembye at gmail.com> |
BugReports: | https://github.com/MikkelVembye/AIscreenR/issues |
License: | GPL (≥ 3) |
URL: | https://mikkelvembye.github.io/AIscreenR/, https://github.com/MikkelVembye/AIscreenR |
NeedsCompilation: | no |
Materials: | NEWS |
CRAN checks: | AIscreenR results |
Reference manual: | AIscreenR.pdf |
Vignettes: |
Using OpenAI's GPT API models for Title and Abstract Screening in Systematic Reviews (source, R code) |
Package source: | AIscreenR_0.1.0.tar.gz |
Windows binaries: | r-devel: AIscreenR_0.1.0.zip, r-release: AIscreenR_0.1.0.zip, r-oldrel: AIscreenR_0.1.0.zip |
macOS binaries: | r-release (arm64): AIscreenR_0.1.0.tgz, r-oldrel (arm64): AIscreenR_0.1.0.tgz, r-release (x86_64): AIscreenR_0.1.0.tgz, r-oldrel (x86_64): AIscreenR_0.1.0.tgz |
Please use the canonical form https://CRAN.R-project.org/package=AIscreenR to link to this page.
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.