Citation

Discussion Paper Details

Please find the details for DP11516 in an easy to copy and paste format below:

Full Details

Title: Reading Between the Lines: Prediction of Political Violence Using Newspaper Text

Author(s): Hannes Felix Mueller and Christopher Rauh

Publication Date: September 2016

Keyword(s): Civil War, conflict, Forecasting, Latent Dirichlet Allocation, Machine Learning, panel data and Topic Models

Programme Area(s): Development Economics

Abstract: This article provides a new methodology to predict armed conflict by using newspaper text. Through machine learning, vast quantities of newspaper text are reduced to interpretable topics. We propose the use of the within-country variation of these topics to predict the timing of conflict. This allows us to avoid the tendency of predicting conflict only in countries where it occurred before. We show that the within-country variation of topics is an extremely robust predictor of conflict and becomes particularly useful when new conflict risks arise. Two aspects seem to be responsible for these features. Topics provide depth because they consist of changing, long lists of terms which makes them able to capture the changing context of conflict. At the same time topics provide width because they summarize all text, including coverage of stabilizing factors.

For full details and related downloads, please visit: https://cepr.org/active/publications/discussion_papers/dp.php?dpno=11516

Bibliographic Reference

Mueller, H and Rauh, C. 2016. 'Reading Between the Lines: Prediction of Political Violence Using Newspaper Text'. London, Centre for Economic Policy Research. https://cepr.org/active/publications/discussion_papers/dp.php?dpno=11516