The Machine Learning for Peace Project is seeking to understand how civic space is changing in countries across the world. Working with partners in the INSPIRES consortium, we identify important shifts in civic space in real time using state of the art machine learning techniques. Using the latest innovations in natural language processing, we classify an enormous corpus of digital news into 19 types of civic space “events” and 22 types of Resurgent Authoritarian Influence (RAI) “events”