Decide Madrid's NLP Toolkit for Citizen Proposals on the Consul Platform

Decide Madrid launched in 2015 under Mayor Manuela Carmena on the open-source Consul platform, growing from 180,000 users in 2016 to 464,654 by 2020 and receiving between 800 and 2,400 proposals a day at peak. The Consul codebase is now stewarded independently by the Consul Democracy Foundation (established 2019) and runs in 135 institutions across 35 countries, reaching an estimated 90 million citizens.

To help the platform cope with that volume, a research team (Miguel Arana-Catania, Felix-Anselm Van Lier, Rob Procter, Nataliya Tkachenko, Yulan He, Arkaitz Zubiaga and Maria Liakata) applied NLP and machine learning directly to Decide Madrid/Consul data, building four capabilities: recommending relevant proposals to citizens, grouping citizens by shared interests, summarising comments on proposals, and helping citizens aggregate and refine overlapping proposals. Their published evaluation concludes that NLP and machine learning 'have a role to play in addressing some of the barriers' platform users faced. A related 'Decide ML' tool was separately built to route proposals to the correct government department.

Governance proved fragile in practice: after Madrid's 2019 change of administration, the city discarded 182 previously approved proposals and halved PB budget resources, a reminder that AI tooling does not by itself guarantee political follow-through. The underlying Consul software is proven highly transferable, but the AI/NLP layer itself has so far been validated mainly in this one Madrid case study.

Read the full analysis: https://democracy-technologies.org/participation/decide-madrid-and-consul/