Access to public open data, particularly European statistical data, represents a significant challenge for many categories of users, from ordinary citizens to research professionals. This paper presents Eurostat Query Assistant (EQUA), an innovative system based on artificial intelligence that enables querying of Eurostat data through natural language. The system implements a specialized multi-agent architecture for thematic domains (such as demographics, economy, climate, health) and customizes responses based on the user’s profile (citizen, journalist, researcher). Thanks to the integration of domain classification techniques, intelligent dataset selection, and automatic SQL query generation, the system effectively interprets natural language requests. The main contribution of this work lies in the democratization of access to Eurostat data, significantly facilitating the use of these resources and promoting greater transparency and civic participation through open data.

EQUA: An AI-Based Approach for Accessing Eurostat Open Data Through Natural Language Queries

Vincenzo Miracula
Primo
;
Giovanni Giuffrida;Calogero Zarba;
2026-01-01

Abstract

Access to public open data, particularly European statistical data, represents a significant challenge for many categories of users, from ordinary citizens to research professionals. This paper presents Eurostat Query Assistant (EQUA), an innovative system based on artificial intelligence that enables querying of Eurostat data through natural language. The system implements a specialized multi-agent architecture for thematic domains (such as demographics, economy, climate, health) and customizes responses based on the user’s profile (citizen, journalist, researcher). Thanks to the integration of domain classification techniques, intelligent dataset selection, and automatic SQL query generation, the system effectively interprets natural language requests. The main contribution of this work lies in the democratization of access to Eurostat data, significantly facilitating the use of these resources and promoting greater transparency and civic participation through open data.
2026
9783032214768
9783032214775
Intelligent Agents
Large Language Models
Linked Open Data
Natural Language Processing
Statistical Data
User-centric Design
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11769/727109
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact