EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Machine Learning for Occupation Coding—A Comparison Study

Malte Schierholz, Matthias Schonlau

Journal of Survey Statistics and Methodology · 11.12.2021 · 9 (5) · 1013-1034

DOI: 10.1093/jssam/smaa023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Survey Statistics and Methodology, online erschienen am 03.11.2020. Verfasst von Malte Schierholz und 1 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: German Institute for Employment Research, Mannheim Centre for European Social Research, German Research Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Asking people about their occupation is common practice in surveys and censuses around the world. The answers are typically recorded in textual form and subsequently assigned (coded) to categories, which have been defined in official occupational classifications. While this coding step is often done manually, substituting it with more automated workflows has been a longstanding goal, promising reduced data-processing costs and accelerated publication of key statistics. Although numerous researchers have developed different algorithms for automated occupation coding, the algorithms have rarely been compared with each other or tested on different data sets. We fill this gap by comparing some of the most promising algorithms found in the literature and testing them on five data sets from Germany. The first two algorithms we test exemplify a common practice in which answers are coded automatically according to a predefined list of job titles. Statistical learning algorithms—that is, regularized multinomial regression, tree boosting, or algorithms developed specifically for occupation coding (algorithms three to six)—can improve upon algorithms one and two, but only if a sufficient number of training observations from previous surveys is available. The best results are obtained by merging the list of job titles with coded answers from previous surveys before using this combined training data for statistical learning (algorithm 7). However, the differences between the algorithms are often small compared to the large variation found across different data sets, which we ascribe to systematic differences in the way the data were coded in the first place. Such differences complicate the application of statistical learning, which risks perpetuating questionable coding decisions from the training data to the future.

Förderung

  • German Institute for Employment Research
  • Mannheim Centre for European Social Research
  • German Research Foundation
  • Social Sciences and Humanities Research Council of Canada
  • Federal Institute for Vocational Education and Training (BIBB) and the Robert Koch Institute

Zitieren

APA

Schierholz, M., & Schonlau, M. (2021). Machine Learning for Occupation Coding—A Comparison Study. Journal of Survey Statistics and Methodology, 9(5), 1013-1034. https://doi.org/10.1093/jssam/smaa023

Vancouver

Schierholz M, Schonlau M. Machine Learning for Occupation Coding—A Comparison Study. Journal of Survey Statistics and Methodology. 2021;9(5):1013-1034. doi:10.1093/jssam/smaa023

BibTeX
@article{Schierholz2021,
  author = {Schierholz, Malte and Schonlau, Matthias},
  title = {Machine Learning for Occupation Coding—A Comparison Study},
  journal = {Journal of Survey Statistics and Methodology},
  year = {2021},
  volume = {9},
  number = {5},
  pages = {1013--1034},
  doi = {10.1093/jssam/smaa023}
}
Kostenlos starten →