Adaptive political questionnaires for voting advice applications
In collaboration with Smartvote, Abraham Bernstein and his PhD student Fynn Bachmann have developed a new algorithm that improves the quality of voting advice.
The Smartvote platform helps voters to find the candidates who most closely match their views from the large number of candidates: Smartvote recommends these candidates on the basis of a questionnaire with over 70 questions. But what happens if not all the questions are answered?
“We wanted to discover a method that gives voters the best possible advice at any point in time regardless of how many questions they have already answered”, explains Abraham Bernstein, Professor at the Department of Informatics and Managing Director of the Digital Society Initiative at the UZH.