Analysing global professional gender gaps using LinkedIn advertising data
Department of Sociology, University of Oxford, 42-43 Park End Street, OX1 1JD, Oxford, United Kingdom
2 Nuffield College, University of Oxford, New Road, OX1 1NF, Oxford, United Kingdom
3 Leverhulme Centre for Demographic Science, University of Oxford, 42-43 Park End Street, OX1 1JD, Oxford, United Kingdom
Accepted: 7 June 2021
Published online: 29 July 2021
Although women’s participation in tertiary education and the labour force has expanded over the past decades, women continue to be underrepresented in technical and managerial occupations. We analyse if gender inequalities also manifest themselves in online populations of professionals by leveraging audience estimates from LinkedIn’s advertisement platform to explore gender gaps among LinkedIn users across countries, ages, industries and seniorities. We further validate LinkedIn gender gaps against ground truth professional gender gap indicators derived from the International Labour Organization’s (ILO) Statistical Database, and examine the feasibility and biases of predicting global professional gender gap indicators using gender gaps computed from LinkedIn’s online population. We find that women are significantly underrepresented relative to men on LinkedIn in countries in Africa, the Middle East and South Asia, among older individuals, in Science, Technology, Engineering and Mathematics (STEM) fields and higher-level managerial positions. Furthermore, a simple, aggregate indicator of the female-to-male ratio of LinkedIn users, which we term the LinkedIn Gender Gap Index (GGI), shows strong positive correlations with ILO ground truth professional gender gaps. A parsimonious regression model using the LinkedIn GGI to predict ILO professional gender gaps enables us to expand country coverage of different ILO indicators, albeit with better performance for general professional gender gaps than managerial gender gaps. Nevertheless, predictions generated using the LinkedIn population show some distinctive biases. Notably, we find that in countries where there is greater gender inequality in internet access, LinkedIn data predict greater gender equality than the ground truth, indicating an overrepresentation of high status women online in these settings. Our work contributes to a growing literature seeking to harness the ‘data revolution’ for global sustainable development by evaluating the potential of a novel data source for filling gender data gaps and monitoring key indicators linked to women’s economic empowerment.
Key words: LinkedIn / Digital Demography / Gender / Sustainable Development Goals / Data for Development
© The Author(s) 2021
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.