How can we leverage big-data to track labour market and skill demands during the COVID-19 crisis?

A Natural Language Processing model approach to the analysis of online job postings.
20 May 2021
20 May 2021
Contatti: 
Doctoral School of Social Sciences
via Verdi 26, 38122 - Trento
Tel. 
+39 0461 283756 - 2290
Fax 
+39 0461 282335

Skype: school.socialsciences

Where: Zoom Platform
Time: 2 p.m.

Please contact school.socialsciences [at] unitn.it

 for the link to the Zoom event.

Speaker

Abstract

New advancements in automated web scraping technologies (i.e. the automated retrieval and storage of textual information from the internet) allow to collect and leverage the richness of the information contained in online job postings and use it to analyse trends in labour market dynamics and skill demands with unprecedented granularity and timeliness.

The presentation will discuss the OECD approach to the analysis of the skill information contained in millions of online vacancies and the various applications of big-data analytics for labour market intelligence during the COVID-19 crisis.

The presentation will also discuss the use of Natural Language Processing (NLP) algorithms to derive a word’s meaning from the context and show how to empirically apply those algorithms to infer the ‘relevance’ of each skill-keyword for a wide range of occupations. Based on this, the presentation will discuss approaches to determine occupational similarity based on skill requirements and ways to leverage this information to suggest feasible retraining pathways to workers displaced during the COVID-19 crisis.

Finally the discussion will provide insights on how to use NLP approaches to determine the degree of ‘transversality’ of skills across jobs and the labour market returns (wage and employment dynamics) that are associated to those.