evidoria

← Back to browse

Good practice Imported

DIPAS — Hamburg's AI-Assisted Digital Participation System for Urban Planning Feedback

Germany · Hamburg · See the Germany profile · See the Hamburg profile

Evidence: Descriptive / self-reported Top 22% 73/100 · Ask Evidence Copilot about this practice

Hamburg's DIPAS platform uses fine-tuned LLaMA and RoBERTa models to automatically cluster and summarise thousands of citizen comments on urban-planning consultations, work that once took five staff over a week — and has since spread to nine other German cities.

>3,000
Citizen contributions processed (cycling consultation)
5 staff, >1 week
Prior manual processing time (comparable consultation)
9
German cities that have adopted DIPAS
DIPAS — Hamburg's AI-Assisted Digital Participation System for Urban Planning Feedback

Details

Maturity
Scaling
Promoter
City of Hamburg (Ministry of Urban Development and Housing) & HafenCity University City Science Lab
Period
2017–ongoing; AI/NLP analytics toolbox developed 2023–2024
Region (NUTS)
DE60
Keywords
urban planning, digital participation, public administration, civic technology

Context

DIPAS is Hamburg's platform for citizen participation in urban planning, launched 2017 by the Ministry of Urban Development and Housing with HafenCity University's City Science Lab.

Activities

Since 2023, DIPAS has integrated fine-tuned LLaMA and RoBERTa models that cluster citizen contributions by theme, distinguish problems from proposed solutions, and map comments to locations.

Results

A cycling-concept consultation drew over 3,000 contributions; a comparable consultation previously required 5 full-time staff more than a week to process manually. DIPAS has since been adopted by 9 other German cities.

Implementation

Indicative cost
Medium (€50k–€500k)
Time to results
Medium (1–3 years)
Staffing & skills
Ministry of Urban Development and Housing, HafenCity University City Science Lab

Conditions for success

  • external audit of clustering algorithms to guard against distortion
  • keeping the platform open source for other cities to adopt

Commonly funded by

Own resources / municipal budget

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful