Francesco Trentini

Osservatorio Statistico sul Terzo Settore

The Statistical Observatory on the Third Sector produces an original database, created by enriching the administrative data from the National Single Register of the Third Sector (RUNTS) of the Ministry of Labour and Social Policies with information collected from the web. In particular, the Observatory processes the textual content of each Third Sector Entity’s (ETS) website using machine learning techniques to verify and enhance the administrative register with information extracted from each ETS’s websites.

The goal of the Observatory is to produce timely and detailed data to represent the Third Sector and is available for research activities that inform public and private policies.

Developed by Carlo Bottai and Francesco Trentini with the financial support of the Bicocca Starting Grant 2023, University of Milano Bicocca.

Related publications:

Carlo Bottai and Francesco Trentini (2025) Mapping the Italian Third Sector: Insights from Web-augmented Administrative Data. LABOR Working Paper no. 196. Also available at SSRN: https://ssrn.com/abstract=5744522 or http://dx.doi.org/10.2139/ssrn.5744522

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.