Using online job postings to predict key labour market indicators.

Autor: Štefánik, Miroslav, Lyócsa, Štefan, Bilka, Matúš
Předmět:
Zdroj: Social Science Computer Review; Oct2023, Vol. 41 Issue 5, p1630-1649, 20p
Abstrakt: Keywords: vacancy statistics; online data; time series; predictive modelling; unemployment; employment EN vacancy statistics online data time series predictive modelling unemployment employment 1630 1649 20 09/26/23 20231001 NES 231001 We explore data collected as an administrative by-product of an online job advertisement portal with dominant market coverage in Slovakia. While the potential of other online data, such as trends in internet searches or social networks, in predicting unemployment was explored in the past (e.g. [3]; [10]; [11]; [21]; [44]), we are not aware of any study exploring trends in the total number of OJVs specifically to predict unemployment or employment. Data We aim to assess the ability of OJV postings to capture and predict the development of official job vacancy, employment and unemployment statistics, which we jointly refer to as key labour market indicators. From the perspective of labour market analysis, OJV data present an even richer source of information than data acquired from online search (e.g. Google Trends) or social networks (e.g. Twitter) because they document a substantial share of the hiring process. [Extracted from the article]
Databáze: Complementary Index