Extracting O*NET Features from the NLx Corpus to Build Public Use Aggregate Labor Market Data
Authors:
Preprint
Abstract
Data from online job postings are difficult to access and are not built in a standard or transparent manner. Data included in the standard taxonomy and occupational information database (O*NET) are updated infrequently and based on small survey samples. We adopt O*NET as a framework for building natural language processing tools that extract structured information from job postings. We publish the Job Ad Analysis Toolkit (JAAT), a collection of open-source tools built for this purpose, and demonstrate its reliability and accuracy in out-of-sample and LLM-as-a-Judge testing. We extract more than 10 billion data points from more than 155 million online job ads provided by the National Labor Exchange (NLx) Research Hub, including O*NET tasks, occupation codes, tools, and technologies, as well as wages, skills, industry, and more features. We describe the construction of a dataset of occupation, state, and industry level features aggregated by monthly active jobs from 2015 - 2025. We illustrate the potential for research and future uses in education and workforce development.Keywords
All Related Versions
This publication has 46 references indexed in Scilit:
- Overview of the TalentCLEF 2025: Skill and Job Title Intelligence for Human Capital Management2025
- Data for labor market concentration using Lightcast (formerly Burning Glass Technologies)Data in Brief, 2024
- The Role of Share Repurchases for Firms’ Social and Environmental SustainabilityJournal of Business Ethics, 2022
- Machine learning and human capital complementarities: Experimental evidence on bias mitigationStrategic Management Journal, 2020
- Strategic entrepreneurial orientation: Configurations, performance, and the effects of industry and timeStrategic Entrepreneurship Journal, 2018
- Speaking of the short-term: disclosure horizon and managerial myopiaReview of Accounting Studies, 2015
- The “task approach” to labor markets: an overviewJournal for Labour Market Research, 2013
- Use of O*NET as a job exposure matrix: A literature reviewAmerican Journal of Industrial Medicine, 2010
- The influence of top management team attention patterns on global strategic posture of firmsJournal of Organizational Behavior, 2005
- Hazardous measures: an interpretive textual analysis of quantitative sensemaking during crisesJournal of Organizational Behavior, 1997