Use CasesInsights
Debate Simulation

Where two electorates converge and where they do not.

The simulation puts two electorates against each other on one topic and checks, statement by statement, what lands with the other camp and what does not. It draws on voice-based interviews with around 1,200 people from all major electorates.

Electorate ATopic: AffordabilityElectorate B
Electorate A - speaking

People on low incomes feel every price rise first.

Adopted: matches statements from the other camp
Common ground
The data

Around 1,800 statements from voice-based interviews.

The statements come from several surveys among around 1,200 people from all major electorates, as of August 2026. They were collected in voice-based interviews, not in focus groups with social pressure.

Every statement sits coded in the system: which concern it expresses, how typical it is for the group, and in what tone it was spoken.

1,200Respondents
1,800Statements
VoiceInterview mode
08/2026As of
The mechanism

How you start a simulation.

You pick two electorates and a topic that moves both. Then you put the two groups into a debate.

01

Two camps form

One stage for each side. A thousand tiny dots standing for the positions of the respondents.

02

Arguments are put forward

In turn, in the diction of each group and close to what was said in the interviews.

03

Some arguments land

When a point from one camp catches on with the other, a group breaks away from the accepting side and stays in the middle. The common ground grows visibly with every concession.

04

Some do not land

Then the system shows why, with a reason that comes out of the interviews rather than an invented category.

The outcome

After about thirty seconds the verdict is in.

And it is not "one side won", but three answers you can keep working with:

What both sides could agree on

Close to how the respondents put it, not translated into marketing language.

Why they do not agree beyond that

With the reasoning of what it would take for them to do so.

What matters to them

As bars, because nobody reads numbers in a row.

And all of it for both sides in parallel, because debates are read across, not end to end.

Why it holds

No script. Material.

The adoptions are traceable

The system does not judge whether an argument sounds convincing. It checks which statements from the interviews come closest to the point being made, and marks the hits. Every adoption traces back to a concrete recording.

The interjections come from the pool

While one side speaks, interjections from the listening group appear at the edge. Short sentences of the kind you know from everyday life. Every debate pulls them fresh from the interviews.

Failure is part of the design

In some constellations there is no convergence. The simulation shows exactly that and explains why. A result of zero is not an error here, it is the finding.

Data protection: participant statements are not shown verbatim. What appears in the simulation is a linguistically smoothed version that keeps the substance and the tone but allows no conclusions about individual people.

Who it is for

A tool against the easy explanation.

The module is for everyone who wants to understand why people vote the way they vote. And above all: under what conditions they would change their mind.

ResearchersCivic and political educationNewsrooms reporting on representation and divisionAnyone who wants to understand what is happening right now

Put two camps into a debate.

Open the simulation

Opens the live simulation in a new tab.

Debate Simulation: Two Electorates in Conversation | VOLTO