Predicting current voting intentions by Big Five personality domains, facets, and nuances – A random forest analysis approach in a German sample

To understand what was driving individual differences in voting intentions a large German sample, we investigated the predictability of from Big Five personality domains, facets, and nuances, thereby tackling shortcomings previous studies. Using random forest analyses dataset N = 4,286 individuals (46.01% men), separate models were trained to predict 1) not vote versus vote, 2) for specific party, 3) left- right-from-the-center party either or nuances (represented by items). Except balanced accuracies marginally exceeded those achieved baseline learner always predicting majority class. over facets domains slightly increased accuracies. Results indicate that additional variables should be considered accurately intentions, at least samples.