Using Past Violence and Current News to Predict Changes in Violence
This article proposes a new method for predicting escalations and de‐escalations of violence using a model which relies on conflict history and text features. The text features are generated from over 3.5 million newspaper articles using a so called topic‐model. We show that the combined model relies to a large extent on conflict dynamics but that text is able to contribute meaningfully in the prediction of rare outbreaks of violence in previously peaceful countries. Given the very powerful dynamics of the conflict trap these cases are particularly important for prevention efforts.
This project is part of a forthcoming special issue in International Interactions which is based on a friendly forecasting competition organized by the VIEWS team. Despite the fact that we did not specialize in intensity predictions we did extremely well in this competition and this encouraged us to make the prediction of the intensity of conflict part of our conflictforecast.org
The resubmitted version of the paper can be downloaded here.