There is a long-standing interest in how the visual appearance of politicians predicts their success. Usually, the scope of such studies is limited by the need for human-rated facial features. We instead fine-tune pre-trained image classification models based on convolutional neural networks to predict facial features of 7,080 Danish politicians. Attractiveness and trustworthiness scores correlate positively and robustly with both ballot paper placement (proxying for intra-party success) and the number of votes gained in local and national elections, while dominance scores correlate inconsistently. Effect sizes are at times substantial. We find no moderation by politician gender or election type. However, dominance scores correlate significantly with outcomes for conservative politicians. We discuss possible causal mechanisms behind our results.

What is the effect of external economic intervention on political support and economic evaluations? We argue that economic interventions systematically worsen support for governing institutions and much of this is mediated through updating economic perceptions, at least during the Eurozone crisis. We evidence this with two analyses. First, we provide the first quasi-experimental evidence to show that intervention worsened both political support and economic evaluations. Second, we conduct a mediation analysis using Eurobarometer data to quantify how much of the effect of intervention is mediated by economic evaluations. This has broader implications for understanding how citizens react to international integration, international cues, and the process of forming judgements of political support.