Skewed signals? Confronting biases in Online Job Ads data

Enrique Fernandez Macias () and Matteo Sostero
Additional contact information
Enrique Fernandez Macias: European Commission - JRC, https://joint-research-centre.ec.europa.eu/index_en
Authors registered in the RePEc Author Service: Enrique Fernandez-Macias

No JRC136599, JRC Research Reports from Joint Research Centre

Abstract: Most job vacancies in advanced economies are advertised online. With big data analytics, they can be converted into useful data for research. This data based on Online Job Ads (OJA) is a very promising source for labour market analysis and skills intelligence: rich in content, granular in detail, and available almost in real-time. This data is increasingly being used, in particular to study the changing nature of skills. Some key findings from OJA data emphasize: 1) The growing importance of digital and soft skills; 2) An acceleration in the rate of change in skills demand; 3) A growing hybridisation of jobs. However, some of these findings may be driven by biases inherent in OJA data, because: 1) It tends to overrepresent high-skill occupations relative to manual ones, particularly in ICT; 2) It covers better skills which are formal and standardised, typically associated to profession-al occupations; 3) It suffers from social desirability bias, with positive and soft attributes being over-emphasized in the vacancy notices. OJA can provide frequent and detailed data on labour market trends, and help identify emerging skills and occupations. However, it suffers from biases and it cannot provide all answers. OJA should complement, rather than replace, data from traditional surveys and administrative sources on the labour market

Date: 2024-01
New Economics Papers: this item is included in nep-big and nep-ict
References: Add references at CitEc
Citations:

Downloads: (external link)
https://publications.jrc.ec.europa.eu/repository/handle/JRC136599 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ipt:iptwpa:jrc136599

Access Statistics for this paper

More papers in JRC Research Reports from Joint Research Centre Contact information at EDIRC.
Bibliographic data for series maintained by Publication Officer ().