During the 2008 presidential transition, when I helped the Obama administration invite Americans to suggest policy proposals for the incoming administration’s first one hundred days, over 125,000 people shared 44,000 ideas and recommendations. While there might have been brilliant ideas in that flood of responses, we had no way to find, let alone act on them. The more people participate, the harder it can be to extract signals from noise.

The more people participate, the harder it can be to extract signals from noise. 

The City of Hamburg is turning to open source artificial intelligence to make sense of citizen feedback on a scale and speed that was once unimaginable.

Watch the recording: Claudius Lieven presents DIPAS, Hamburg’s AI-powered citizen feedback platform, at the InnovateUS workshop on AI and Citizen Engagement (Oct 16, 2025). 

The Digital Participation System (DIPAS) is Hamburg, Germany’s integrated digital participation platform, designed to let residents contribute ideas, comments, and feedback on urban development projects online or in workshops. It combines mapping, document sharing, and discussion tools so that citizens can engage directly with concrete plans for their neighborhoods. 

City officials had long struggled with the fact that while citizens submitted thousands of comments on planning projects, only a fraction could realistically be read and processed.

“We take the promise of participation seriously,” explained Claudius Lieven, one of DIPAS’s creators in Hamburg's Ministry of Urban Development and Housing. “If people contribute, their collective intelligence must count. But with so many inputs, we simply couldn’t keep up.” 

Making sense of feedback from a single engagement could once occupy five full-time employees for more than a week and chill any desire to do a follow-up conversation. 

As a result, Lieven and his team spent three years integrating AI into the open-source system to make the new analytics toolbox more useful and the government more responsive. They combined the fine-tuning of Facebook’s advanced open-source language models LLaMA and RoBERTa with topic modeling and geodata integration. 

With AI, DIPAS can cluster and summarize thousands of comments and distinguish between a “major position” about the current situation (for example, “The bike path is unsafe”) and an “idea” proposing what should be done (“The bike path should have better lighting”).

The impact is tangible. When Hamburg sought feedback on a new cycling concept for one of its boroughs, residents submitted over three thousand contributions. The system automatically organizes comments into themes such as crossing safety or continuous bike lanes so that citizens and policymakers can see and use them. 

DIPAS leverages AI to both extract the core points from each submission. In addition, it links comments to the specific location the resident has indicated on a map. For example, a comment about lighting a bike path is tied directly to the relevant street on a map, so officials can see where concerns and proposals are concentrated. Work is underway to extend this automated linking to features like schools or institutions. 

Because the system structures and categorizes inputs, it also enables much more comprehensive reporting than was previously possible. Officials can quickly generate summaries that show the most frequent concerns, visualize patterns across neighborhoods, and produce clear charts and maps. These structured analyses feed directly into political deliberations and shape the final plan.

In other cases, DIPAS has enabled faster government response. When clusters of complaints about noise or waste emerged, the system made it immediately clear where problems were concentrated. 

Technology does not make decisions, but by transforming an overwhelming flood of comments into actionable intelligence, including visualizations, DIPAS analytics helps to ensure that good ideas are not lost.

The success is evident. Nine German cities have already adopted the platform to help leaders listen better, act faster, and govern more responsively.  In an age of digital noise, Hamburg has found a way to turn voices into vision.