{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T17:50:45Z","timestamp":1784569845997,"version":"3.55.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Deutsches Zentrum f\u00fcr Hochschul- und Wissenschaftsforschung GmbH (DZHW)"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Artif Intell"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Occupation coding is the classification of information on occupation that is collected in the context of demographic variables. Occupation coding is an important, but a tedious task for researchers in social science and official statistics that calls for automation. Due to the complexity of the task, currently, researchers carry out hand-coding or computer-assisted coding. However, we argue that, with the rise of transformer-based language models, hand-coding can be displaced by models, such as BERT or GPT3. Hence, we compare these models with state-of-the-art encoding approaches, showing that language models have a clear advantage in Cohen\u2019s kappa compared to related approaches, but also allow for flexible fine-grained coding of single digits. Taking into consideration the hierarchical structure of the occupational group, we also develop an approach that achieves better performance for the classification of different single digit combinations.<\/jats:p>","DOI":"10.1007\/s44163-023-00050-y","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T13:49:51Z","timestamp":1676296191000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Automated occupation coding with hierarchical features: a data-centric approach to classification with pre-trained language models"],"prefix":"10.1007","volume":"3","author":[{"given":"Parisa","family":"Safikhani","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayastan","family":"Avetisyan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dennis","family":"F\u00f6ste-Eggers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Broneske","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,13]]},"reference":[{"issue":"12","key":"50_CR1","doi-asserted-by":"publisher","first-page":"2100","DOI":"10.1016\/j.socscimed.2010.09.026","volume":"71","author":"K Fujishiro","year":"2010","unstructured":"Fujishiro K, Xu J, Gong F. What does \u201coccupation\u2019\u2019 represent as an indicator of socioeconomic status?: Exploring occupational prestige and health. Soc Sci Med. 2010;71(12):2100\u20137.","journal-title":"Soc Sci Med"},{"key":"50_CR2","first-page":"205979911663800","volume":"9","author":"R Connelly","year":"2016","unstructured":"Connelly R, Gayle V, Lambert PS. A review of occupation-based social classifications for social survey research. Methodol Innov. 2016;9:2059799116638003.","journal-title":"Methodol Innov"},{"key":"50_CR3","doi-asserted-by":"crossref","unstructured":"Schooler C, Schoenbach C. Social class, occupational status, occupational self-direction, and job income: A cross-national examination. In: Sociological Forum, vol. 9, pp. 431\u2013458 (1994). Springer.","DOI":"10.1007\/BF01466317"},{"issue":"6","key":"50_CR4","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1086\/220615","volume":"55","author":"PK Hatt","year":"1950","unstructured":"Hatt PK. Occupation and social stratification. Am J Sociol. 1950;55(6):533\u201343.","journal-title":"Am J Sociol"},{"issue":"1","key":"50_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40711-020-00128-5","volume":"7","author":"Y Qi","year":"2020","unstructured":"Qi Y, Liang T, Ye H. Occupational status, working conditions, and health: evidence from the 2012 china labor force dynamics survey. J Chin Sociol. 2020;7(1):1\u201323.","journal-title":"J Chin Sociol"},{"issue":"1","key":"50_CR6","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/s11577-020-00673-4","volume":"72","author":"B Christoph","year":"2020","unstructured":"Christoph B, Matthes B, Ebner C. Occupation-based measures-an overview and discussion. KZfSS K\u00f6lner Zeitschrift f\u00fcr Soziologie und Sozialpsychologie. 2020;72(1):41\u201378.","journal-title":"KZfSS K\u00f6lner Zeitschrift f\u00fcr Soziologie und Sozialpsychologie"},{"issue":"4","key":"50_CR7","doi-asserted-by":"publisher","first-page":"981","DOI":"10.2478\/jos-2021-0042","volume":"37","author":"DN Peycheva","year":"2021","unstructured":"Peycheva DN, Sakshaug JW, Calderwood L. Occupation coding during the interview in a web-first sequential mixed-mode survey. J Off Stat. 2021;37(4):981\u20131007.","journal-title":"J Off Stat"},{"issue":"3","key":"50_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1177\/146879410100100303","volume":"1","author":"TJ Rapley","year":"2001","unstructured":"Rapley TJ. The art (fulness) of open-ended interviewing: some considerations on analysing interviews. Qual Res. 2001;1(3):303\u201323.","journal-title":"Qual Res"},{"key":"50_CR9","unstructured":"Klassifikation\u00a0der Berufe K. Band 1: Systematischer und alphabetischer Teil mit Erl\u00e4uterungen. Bundesagentur f\u00fcr Arbeit (2010)"},{"key":"50_CR10","volume-title":"International Standard Classification of Occupations 2008 (ISCO-08): Structure, Group Definitions and Correspondence Tables","author":"IL Office","year":"2012","unstructured":"Office IL. International Standard Classification of Occupations 2008 (ISCO-08): Structure, Group Definitions and Correspondence Tables. Geneva: International Labour Office; 2012."},{"key":"50_CR11","unstructured":"Gendlin A, Viechnicki P. Computer-assisted historical occupation coding. URL: https:\/\/scholar.google.com\/scholar?hl=de&as_sdt=0%2C5&q=+Gendlin+A%2C+Viechnicki+P.+Computer-assisted+historical+occupation+coding.&btnG="},{"issue":"5","key":"50_CR12","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1093\/jssam\/smaa023","volume":"9","author":"M Schierholz","year":"2021","unstructured":"Schierholz M, Schonlau M. Machine learning for occupation coding-a comparison study. J Surv Stat Methodol. 2021;9(5):1013\u201334.","journal-title":"J Surv Stat Methodol"},{"key":"50_CR13","unstructured":"Z\u00fcll C. The coding of occupations. GESIS Survey Guidelines. 2016."},{"key":"50_CR14","unstructured":"Schierholz M. Automating survey coding for occupation. PhD thesis; 2014."},{"issue":"1","key":"50_CR15","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1515\/jos-2017-0006","volume":"33","author":"H Gweon","year":"2017","unstructured":"Gweon H, Schonlau M, Kaczmirek L, Blohm M, Steiner S. Three methods for occupation coding based on statistical learning. J Off Stat. 2017;33(1):101\u201322.","journal-title":"J Off Stat"},{"issue":"4","key":"50_CR16","first-page":"23","volume":"12","author":"J Lim","year":"2021","unstructured":"Lim J, Moon H, Lee C, Woo C, Lim H. An automated industry and occupation coding system using deep learning. J Korea Converg Soc. 2021;12(4):23\u201330.","journal-title":"J Korea Converg Soc"},{"key":"50_CR17","unstructured":"Decorte J-J, Van\u00a0Hautte J, Demeester T, Develder C. Jobbert: Understanding job titles through skills. arXiv preprint arXiv:2109.09605. 2021."},{"issue":"8","key":"50_CR18","doi-asserted-by":"publisher","first-page":"16422","DOI":"10.2196\/16422","volume":"4","author":"H Bao","year":"2020","unstructured":"Bao H, Baker CJ, Adisesh A, et al. Occupation coding of job titles: iterative development of an automated coding algorithm for the Canadian national occupation classification (aca-noc). JMIR Form Res. 2020;4(8):16422.","journal-title":"JMIR Form Res"},{"key":"50_CR19","volume-title":"S-464 Automated Occupational Encoding to the Canadian National Occupation Classification using an Ensemble Classifier from TF-IDF and Doc2Vec Embeddings","author":"CAS Garcia","year":"2021","unstructured":"Garcia CAS, Adisesh A, Baker CJ. S-464 Automated Occupational Encoding to the Canadian National Occupation Classification using an Ensemble Classifier from TF-IDF and Doc2Vec Embeddings. London: BMJ Publishing Group Ltd; 2021."},{"key":"50_CR20","unstructured":"Savic N, Bovio N, Gilbert F, Canu IG. Procode: the swiss multilingual solution for automatic coding and recoding of occupations and economic activities. arXiv preprint arXiv:2012.07521. 2020."},{"key":"50_CR21","unstructured":"Tiemann M, Kaiser F. Klassifikationen der Berufe-Begriffliche Grundlagen, Vorgehensweise, Anwendungsfelder. na, Bonn; 2013."},{"key":"50_CR22","doi-asserted-by":"publisher","unstructured":"Kraft MHG. How important are linguistic competencies on the german labour market? a qualitative content analysis of job advertisements.\u00a0EJEBS. 2021;v5i3:35\u201341.\u00a0https:\/\/doi.org\/10.26417\/ejes.","DOI":"10.26417\/ejes"},{"key":"50_CR23","unstructured":"Geis-Th\u00f6ne W. Zuwanderung hat den gesundheitsbereich gest\u00e4rkt. Technical report, IW-Kurzbericht; 2020."},{"key":"50_CR24","unstructured":"Koebe J, Samtleben C, Schrenker A, Zucco A. Systemically relevant but little recognized: Compensation of indispensable occupations underperformed in the Corona crisis. 2020.\u00a0https:\/\/www.diw.de\/de\/diw_01.c.792754.de\/publikationen\/diw_aktuell\/2020_0048\/systemrelevant__aber_dennoch_kaum_anerkannt__entlohnung_unverzichtbarer_berufe_in_der_coronakrise_unterdurchschnittlich.html."},{"issue":"4","key":"50_CR25","doi-asserted-by":"publisher","first-page":"551","DOI":"10.25162\/zbw-2018-0019","volume":"114","author":"J Guggemos","year":"2018","unstructured":"Guggemos J. Analyse beruflicher t\u00e4tigkeitsfelder von wirtschaftsp\u00e4dagogen\/-innen anhand von daten des karriereportals xing. Zeitschrift f\u00fcr Berufs-und Wirtschaftsp\u00e4dagogik. 2018;114(4):551\u201377.","journal-title":"Zeitschrift f\u00fcr Berufs-und Wirtschaftsp\u00e4dagogik"},{"key":"50_CR26","unstructured":"Diel A. Ein viertel der pharmabesch\u00e4ftigten arbeitet in der produktion. Technical report, IW-Kurzbericht; 2019."},{"issue":"1","key":"50_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12888-018-1645-7","volume":"18","author":"F Frank","year":"2018","unstructured":"Frank F, Jablotschkin M, Arthen T, Riedel A, Fangmeier T, H\u00f6lzel LP, Tebartz\u00a0van Elst L. Education and employment status of adults with autism spectrum disorders in Germany\u2013a cross-sectional-survey. BMC Psychiatry. 2018;18(1):1\u201310","journal-title":"BMC Psychiatry"},{"issue":"8","key":"50_CR28","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I, et al. Language models are unsupervised multitask learners. OpenAI blog. 2019;1(8):9.","journal-title":"OpenAI blog"},{"issue":"140","key":"50_CR29","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou Y, Li W, Liu PJ, et al. Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res. 2020;21(140):1\u201367.","journal-title":"J Mach Learn Res."},{"key":"50_CR30","unstructured":"Luo L, Wang Y. Emotionx-hsu: Adopting pre-trained bert for emotion classification. arXiv preprint arXiv:1907.09669. 2019."},{"key":"50_CR31","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. 2018."},{"key":"50_CR32","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, et al. Language models are few-shot learners. Adv Neural Inf Process Syst. 2020;33:1877\u2013901.","journal-title":"Adv Neural Inf Process Syst"},{"key":"50_CR33","doi-asserted-by":"crossref","unstructured":"Chan B, Schweter S, M\u00f6ller T. German\u2019s next language model. arXiv preprint arXiv:2010.10906. 2020.","DOI":"10.18653\/v1\/2020.coling-main.598"},{"key":"50_CR34","unstructured":"Radford A, Narasimhan K, Salimans T, Sutskever I. Improving language understanding by generative pre-training (2018)"},{"issue":"3","key":"50_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439726","volume":"54","author":"S Minaee","year":"2021","unstructured":"Minaee S, Kalchbrenner N, Cambria E, Nikzad N, Chenaghlu M, Gao J. Deep learning-based text classification: a comprehensive review. ACM Computing Surveys (CSUR). 2021;54(3):1\u201340.","journal-title":"ACM Computing Surveys (CSUR)"},{"issue":"4","key":"50_CR36","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1007\/s11023-020-09548-1","volume":"30","author":"L Floridi","year":"2020","unstructured":"Floridi L, Chiriatti M. Gpt-3: its nature, scope, limits, and consequences. Minds Mach. 2020;30(4):681\u201394.","journal-title":"Minds Mach"},{"key":"50_CR37","unstructured":"Ng A, Laird D, He L. Data-centric ai competition. DeepLearning AI. 2021. https:\/\/deeplearning-ai.github.io\/data-centric-comp\/. Accessed 9 Dec 2021."},{"key":"50_CR38","unstructured":"Andrew Ng. Yearning for machine learning. 2018.\u00a0https:\/\/info.deeplearning.ai\/machine-learning-yearning-book."}],"container-title":["Discover Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-023-00050-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44163-023-00050-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44163-023-00050-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T14:04:58Z","timestamp":1676297098000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44163-023-00050-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,13]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["50"],"URL":"https:\/\/doi.org\/10.1007\/s44163-023-00050-y","relation":{},"ISSN":["2731-0809"],"issn-type":[{"value":"2731-0809","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,13]]},"assertion":[{"value":"22 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6"}}