Using online vacancy and job applicants’ data to study skills dynamics

Abstract

We assess whether online data on vacancies and applications to a job board are a suitable source for studying skills dynamics outside of Europe and the United States, where a rich literature has examined skills dynamics using online vacancy data. Yet, the knowledge on skills dynamics is scarce for other countries, irrespective of their level of development. We first propose a taxonomy that systematically aggregates three broad categories of skills – cognitive, socioemotional and manual – and fourteen commonly observed and recognizable skills sub-categories, which we define based on unique skills identified through keywords and expressions. Our aim is to develop a taxonomy that is comprehensive but succinct, suitable for the labour market realities of developing and emerging economies and adapted to online vacancies and applicants’ data. Using machine-learning techniques, we then develop a methodology that allows implementing the skills taxonomy in online vacancy and applicants’ data, thus capturing both the supply and the demand side. Implementing the methodology with Uruguayan data from the job board BuscoJobs, we assign skills to 64 per cent of applicants’ employment spells and 94 per cent of vacancies. We consider this a successful implementation since the exploited text information often does not follow a standardized format. The advantage of our approach is its reliance on data that is currently available in many countries across the world, thereby allowing for country-specific analysis that does not need to assume that occupational skills bundles are the same across countries. To the best of our knowledge, we are the first to explore this approach in the context of emerging economies.

What has been driving work-to-work transitions in the emerging world?

“…Finally, an emerging body of evidence (Adhvaryu and Nyshadham, forthcoming;Dimitriadis and Koning, 2022;Chioda and Carney, 2021) highlights the importance of skills for labour market outcomes in LMIC and identifies the relationship of various types of skills and transitions to better jobs as avenues for future empirical research (Bennett et al, 2022;Deming, 2022). We thus investigate the possible relationship between transitioning and skills by including cognitive skills measures in our main estimation.…”

Who creates jobs with broad skillsets?

“…The present paper aims at filling this gap and examines the extent of firm-level differences in the skills demanded within even narrowly-defined occupation categories, and how firm characteristics map into the demand for specific skills. We study this in the case of the labor market of India, using online vacancy data matched with comprehensive firm-level data and relying on an innovative skill taxonomy and methodology to implement it using vacancy data developed by the ILO Research Department for developing and emerging economies (Bennett et al, 2022) comprising information on digital, other cognitive, 1 manual and socio-emotional skills.…”

“…We refer to these skills as "other cognitive skills" since the skill classification by Bennett et al (2022) includes "digital skills" as a subset of "cognitive skills". In this work, we analyze digital and cognitive skills separately, as you will see in the following sections.…”

“…Construction of the skill variables. -We create the skill variables using the skill taxonomy developed by Bennett et al (2022). Drawing from labour economics and psychology literature, this taxonomy distinguishes between the broad categories of cognitive skills, socio-emotional skills, and manual skills, divided into fourteen more detailed sub-categories.…”

“…For the various analysis we present in the paper, we divide cognitive skills into two categories: digital skills and other cognitive skills. It is worth noting that while Bennett et al (2022) include digital skills as a sub-skill within the broader category of cognitive skills, we disaggregated these two types of skills in this study.…”