A Transformer Based Semantic Analysis of (non-English) Danish Jobads

Morten Mathiasen, Jacob Nielsen, Simon Laub

2023

Abstract

To benefit educational adaption and guidance of the unemployed, we report on our study of automated monitorization of labor market demands by analyzing online job ads. We identify and measure two categories of competence demands, “technical competences” and “personal competences”, as well as competences described by Bloom’s taxonomy. Ads are labelled, both by humans and by natural language processing (NLP) transformers. Within all competence categories and levels of Bloom’s taxonomy we demonstrate how the automated NLP transformer process do a semantic search with the same level of precision as the humans.

Paper Citation

in Harvard Style

Mathiasen M., Nielsen J. and Laub S. (2023). A Transformer Based Semantic Analysis of (non-English) Danish Jobads. In Proceedings of the 15th International Conference on Computer Supported Education - Volume 1: CSEDU, ISBN 978-989-758-641-5, SciTePress, pages 359-366. DOI: 10.5220/0012008400003470

in Bibtex Style

@conference{csedu23,
author={Morten Mathiasen and Jacob Nielsen and Simon Laub},
title={A Transformer Based Semantic Analysis of (non-English) Danish Jobads},
booktitle={Proceedings of the 15th International Conference on Computer Supported Education - Volume 1: CSEDU,},
year={2023},
pages={359-366},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012008400003470},
isbn={978-989-758-641-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Conference on Computer Supported Education - Volume 1: CSEDU,
TI - A Transformer Based Semantic Analysis of (non-English) Danish Jobads
SN - 978-989-758-641-5
AU - Mathiasen M.
AU - Nielsen J.
AU - Laub S.
PY - 2023
SP - 359
EP - 366
DO - 10.5220/0012008400003470
PB - SciTePress