labourR: Classify Multilingual Labour Market Free-Text to Standardized Hierarchical Occupations

Allows the user to map multilingual free-text of occupations to a broad range of standardized classifications. The package facilitates automatic occupation coding (see, e.g., Gweon et al. (2017) <doi:10.1515/jos-2017-0006> and Turrell et al. (2019) <doi:10.3386/w25837>), where the ISCO to ESCO mapping is exploited to extend the occupations hierarchy, Le Vrang et al. (2014) <doi:10.1109/mc.2014.283>. Document vectorization is performed using the multilingual ESCO corpus. A method based on the nearest neighbor search is used to suggest the closest ISCO occupation.

Package details

AuthorAlexandros Kouretsis [aut, cre], Andreas Bampouris [aut], Petros Morfiris [aut], Konstantinos Papageorgiou [aut], Stavros Ladas [ctb], Athanassios Siaperas [ctb], Philippe Tissot [ctb], Nikos Vaslamatzis [ctb], Eworx S.A [cph]
MaintainerAlexandros Kouretsis <ako@eworx.gr>
LicenseGPL-3
Version1.0.0
URL https://github.com/AleKoure/labourR
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:
install.packages("labourR")

Try the labourR package in your browser

Any scripts or data that you put into this service are public.

labourR documentation built on July 18, 2020, 5:06 p.m.