{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T18:07:48Z","timestamp":1772906868964,"version":"3.50.1"},"reference-count":23,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2025,2,12]],"date-time":"2025-02-12T00:00:00Z","timestamp":1739318400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Digit. Gov.: Res. Pract."],"published-print":{"date-parts":[[2025,3,31]]},"abstract":"<jats:p>Labor market information is an important input to labor, workforce, education, and macroeconomic policy. However, granular and real-time data on labor market trends are lacking; publicly available data from survey samples are released with significant lags and miss critical information such as skills and benefits. We use generative Artificial Intelligence to automatically extract structured labor market information from unstructured online job postings for the entire U.S. labor market. To demonstrate our methodology, we construct a sample of 6,800 job postings stratified by 68 major occupational groups, extract structured information on educational requirements, remote-work flexibility, full-time availability, and benefits, and show how these job characteristics vary across occupations. As a validation, we compare frequencies of educational requirements by occupation from our sample to survey data and find no statistically significant difference. Finally, we discuss the scalability to collections of millions of job postings. Our results establish the feasibility of measuring labor market trends at scale from online job postings thanks to advances in generative AI techniques. Improved access to such insights at scale and in real-time could transform the ability of policy leaders, including federal and state agencies and education providers, to make data-informed decisions that better support the American workforce.<\/jats:p>","DOI":"10.1145\/3674847","type":"journal-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T11:02:09Z","timestamp":1720695729000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Extracting Structured Labor Market Information from Job Postings with Generative AI"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0764-4090","authenticated-orcid":false,"given":"Mark","family":"Howison","sequence":"first","affiliation":[{"name":"Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2746-2867","authenticated-orcid":false,"given":"William O.","family":"Ensor","sequence":"additional","affiliation":[{"name":"Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9391-5654","authenticated-orcid":false,"given":"Suraj","family":"Maharjan","sequence":"additional","affiliation":[{"name":"Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2710-3742","authenticated-orcid":false,"given":"Rahil","family":"Parikh","sequence":"additional","affiliation":[{"name":"Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1847-8398","authenticated-orcid":false,"given":"Srinivasan H.","family":"Sengamedu","sequence":"additional","affiliation":[{"name":"Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7090-9002","authenticated-orcid":false,"given":"Paul","family":"Daniels","sequence":"additional","affiliation":[{"name":"National Association of State Workforce Agencies, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5980-8711","authenticated-orcid":false,"given":"Amber","family":"Gaither","sequence":"additional","affiliation":[{"name":"National Association of State Workforce Agencies, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4933-6338","authenticated-orcid":false,"given":"Carrie","family":"Yeats","sequence":"additional","affiliation":[{"name":"National Association of State Workforce Agencies, Washington, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2839-3662","authenticated-orcid":false,"given":"Chandan K.","family":"Reddy","sequence":"additional","affiliation":[{"name":"Virginia Polytechnic Institute and State University, Blacksburg, United States and Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8674-9498","authenticated-orcid":false,"given":"Justine S.","family":"Hastings","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, United States and Amazon.com Inc, Seattle, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,2,12]]},"reference":[{"key":"e_1_3_1_2_2","article-title":"Jobs lost, jobs gained: Workforce transitions in a time of automation","author":"Manyika James","year":"2017","unstructured":"James Manyika, Susan Lund, Michael Chui, Jacques Bughin, Jonathan Woetzel, Parul Batra, Ryan Ko, and Saurabh Sanghvi. 2017. Jobs lost, jobs gained: Workforce transitions in a time of automation. McKinsey Global Institute. Retrieved from https:\/\/www.mckinsey.com\/featured-insights\/future-of-work\/jobs-lost-jobs-gained-what-the-future-of-work-will-mean-for-jobs-skills-and-wages","journal-title":"McKinsey Global Institute"},{"key":"e_1_3_1_3_2","unstructured":"National Association of State Workforce Agencies. 2023. Legislative Priorities: Data Infrastructure. Retrieved from https:\/\/www.naswa.org\/advocacy\/government-relations\/2023-legislative-priorities"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1093\/oxrep\/graa033"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpubeco.2020.104235"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1002\/ajim.22928"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.2196\/medinform.4839"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1136\/oemed-2015-103152"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.5271\/sjweh.3613"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2023.100757"},{"key":"e_1_3_1_11_2","unstructured":"Sarah H. Bana. 2021. job2vec: Using language models to understand wage premia. Retrieved from https:\/\/conference.iza.org\/conference_files\/DATA_2021\/bana_s26582.pdf"},{"key":"e_1_3_1_12_2","article-title":"Garbage\u201d surveys erode US data confidence","author":"Anstey Chris","year":"2023","unstructured":"Chris Anstey. 2023. \u201cGarbage\u201d surveys erode US data confidence. Bloomberg. Retrieved from https:\/\/www.bloomberg.com\/news\/newsletters\/2023-02-15\/us-economic-data-why-surveys-for-jolts-and-payroll-numbers","journal-title":"Bloomberg"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Pawel Adrjan and Reamonn Lydon. 2023. What do wages in online job postings tell us about wage growth? SSRN. Retrieved from 10.2139\/ssrn.4451751","DOI":"10.2139\/ssrn.4451751"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.31219\/osf.io\/thg23"},{"key":"e_1_3_1_15_2","unstructured":"White House Council of Economic Advisers. 2018. Addressing america's reskilling challenge. Retrieved from https:\/\/trumpwhitehouse.archives.gov\/briefings-statements\/cea-report-addressing-americas-reskilling-challenge\/"},{"key":"e_1_3_1_16_2","article-title":"Closing the skills gap: Creating workforce-development programs that work for everyone","author":"Laboissiere Martha","year":"2017","unstructured":"Martha Laboissiere and Mona Mourshed. 2017. Closing the skills gap: Creating workforce-development programs that work for everyone. McKinsey & Company. Retrieved from https:\/\/www.mckinsey.com\/industries\/education\/our-insights\/closing-the-skills-gap-creating-workforce-development-programs-that-work-for-everyone","journal-title":"McKinsey & Company"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.7249\/RR2768"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4371445"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.telpol.2022.102310"},{"key":"e_1_3_1_20_2","unstructured":"Korn Ferry. 2018. Future of work: The global talent crunch. Retrieved from https:\/\/www.kornferry.com\/content\/dam\/kornferry\/docs\/pdfs\/KF-Future-of-Work-Talent-Crunch-Report.pdf"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1257\/mac.20190196"},{"key":"e_1_3_1_22_2","unstructured":"U.S. Bureau of Labor Statistics. 2018. Standard occupational classification (SOC) system. Retrieved from https:\/\/www.bls.gov\/soc\/2018\/home.htm"},{"key":"e_1_3_1_23_2","unstructured":"Amazon Web Services. 2023. Amazon bedrock user guide: Prompt engineering guidelines. Retrieved from https:\/\/docs.aws.amazon.com\/bedrock\/latest\/userguide\/prompt-engineering-guidelines.html"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.3386\/w31984"}],"container-title":["Digital Government: Research and Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674847","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:56Z","timestamp":1750291556000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,12]]},"references-count":23,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,3,31]]}},"alternative-id":["10.1145\/3674847"],"URL":"https:\/\/doi.org\/10.1145\/3674847","relation":{},"ISSN":["2691-199X","2639-0175"],"issn-type":[{"value":"2691-199X","type":"print"},{"value":"2639-0175","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,12]]},"assertion":[{"value":"2024-01-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-26","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}