Francesco Trentini

PIAAC2ESCO An AI-driven classification of the PIAAC Background questionnaire onto the ESCO Skills Pillar.

The dataset provides the link between questions of the PIAAC background questionnaire (Cycle 1) and a list of corresponding ESCO skills (v1.0.8). The linkage is done using AI in a framework combining word embeddings, selection of the best embedding, taxonomy alignment, and experts’ validation.

The dataset is freely available on UniData.

Developed by Fabio Mercorio, Mario Mezzanzanica, Filippo Pallucchini and Francesco Trentini of the Interuniversity Research Centre on Public Services (CRISP) and Yuchen Guo, Christina Langer and Simon Wiederhold of the Katholische Universität Eichstätt-Ingolstadt (KU) within the framework of the European Union's Horizon 2020 Pillars - Pathways to inclusive labour markets.

Citation: Mercorio, Fabio. (2021-2022) PIAAC2ESCO – An AI-driven classification of the PIAAC Background questionnaire onto the ESCO Skills Pillar. Mezzanzanica, Mario [Producer]. Pallucchini, Filippo [Producer]. Trentini, Francesco [Producer]. Guo, Yuchen [Producer]. Langer, Christina [Producer]. UniData - Bicocca Data Archive, Milan. Study Number SI399. Data file version 1.0 doi:10.20366/unimib/unidata/SI399-1.0

Matching procedure for CICO - LoSai datasets

The resources allow to replicate the preparation of the dataset combining the Campione Integrato delle Comunicazioni Obbligatorie - CICO (Ministero del Lavoro e delle Politiche Sociali) and the Longitudinal Sample INPS - LoSAI (INPS).

An application of the matching is presented together with a methodological appendix in English in the paper Fabio Berton, Lia Pacelli, Roberto Quaranta, Francesco Trentini (2023), Patterns of labour market reforms: a regional approach to the Italian 'Jobs Act', Sinappsi, XIII, n.1, pp.50-67. DOI: https://doi.org/10.53223/Sinappsi_2023-01-4.

The procedure was tested on CICO-LoSai data updated to July 2021. The choices of sample selection and matching keys are consistent with the research design, aimed at assessing the impact of the policies in question on transformations and activations of employment contracts. We therefore suggest evaluating other matching keys depending on the events one is interested in observing.

The dataset is freely available on GitHub. The methodological note is available in the same repository.