PollyVote: Computational Campaign Coverage (Round 3)

Germany Project type: medium PollyVote


We aim to help newsrooms to improve their election forecasting. We will develop a fully automated and adaptable prediction platform that offers evidence-based election forecasts for potentially any election worldwide. The forecasts will be accompanied by automatically generated narratives and visualizations in multiple languages and for different channels and target audiences, which put the forecasts in context and appropriately communicate their underlying uncertainty in an objective manner. 

The solution

Recent failures to predict major elections (e.g., Brexit, Trump) has eroded trust in our ability to predict the future. As a result, many newsrooms are now reluctant to incorporate election forecasts in their campaign coverage. Others simply lack the necessary skills and resources to develop reliable forecasts. We will (re-)build trust in election forecasting through strict adherence to evidence-based principles for both developing forecasts and communicating their underlying uncertainty. In addition, we will use innovative technological solutions to generate automated election coverage, optimized for different channels and user types, and in multiple languages.