Automatic definition of engineer archetypes: A text mining approach

  • Francesco Lupi*
  • , Mohammed M. Mabkhot
  • , Eleonora Boffa
  • , Pedro Ferreira
  • , Dario Antonelli
  • , Antonio Maffei
  • , Niels Lohse
  • , Michele Lanzetta
  • *Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

151 Downloads (Pure)

Abstract

With the rapid and continuous advancements in technology, as well as the constantly evolving competences required in the field of engineering, there is a critical need for the harmonization and unification of engineering professional figures or archetypes. The current limitations in tymely defining and updating engineers' archetypes are attributed to the absence of a structured and automated approach for processing educational and occupational data sources that evolve over time. This study aims to enhance the definition of professional figures in engineering by automating archetype definitions through text mining and adopting a more objective and structured methodology based on topic modeling. This will expand the use of archetypes as a common language, bridging the gap between educational and occupational frameworks by providing a unified and up-to-date engineering professional figure tailored to a specific period, specialization type, and level. We validate the automatically defined industrial engineer archetype against our previously manually defined profile.

Original languageEnglish
Article number103996
Number of pages17
JournalComputers in Industry
Volume152
Early online date8 Aug 2023
DOIs
Publication statusPublished - Nov 2023

Bibliographical note

Publisher Copyright:
© 2023 The Authors

Keywords

  • Archetype
  • Engineering
  • Industry 4.0
  • Latent dirichlet allocation
  • Professional profile
  • Text mining

ASJC Scopus subject areas

  • General Computer Science
  • General Engineering

Fingerprint

Dive into the research topics of 'Automatic definition of engineer archetypes: A text mining approach'. Together they form a unique fingerprint.

Cite this