We adapt simple tools from computational linguistics to construct a new measure of political risk faced by individual US firms: the share of their quarterly earnings conference calls that they devote to political risks. We validate our measure by showing it correctly identifies calls containing...

We construct new measures of country risk and sentiment as perceived by global investors and executives using textual analysis of the quarterly earnings calls of publicly listed firms around the world. Our quarterly measures cover 45 countries from 2002-2020. We use our measures to provide a...