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

Hannes Mueller and Christopher Rauh

No 11516, CEPR Discussion Papers from Centre for Economic Policy Research

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.

Keywords: Conflict; Civil war; Forecasting; Machine learning; Panel data; Topic models; Latent dirichlet allocation (search for similar items in EconPapers)
JEL-codes: C81 H12 H56 O11 (search for similar items in EconPapers)
Date: 2016-09
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (4)

Downloads: (external link)
https://cepr.org/publications/DP11516 (application/pdf)

Related works:
Journal Article: Reading Between the Lines: Prediction of Political Violence Using Newspaper Text (2018)
Working Paper: Reading Between the Lines: Prediction of Political Violence Using Newspaper Text (2017)
Working Paper: Reading Between the Lines: Prediction of Political Violence Using Newspaper Text (2016)
Working Paper: Reading Between the Lines: Prediction of Political Violence Using Newspaper Text (2016)
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:cpr:ceprdp:11516

Ordering information: This working paper can be ordered from
https://cepr.org/publications/DP11516

Access Statistics for this paper

More papers in CEPR Discussion Papers from Centre for Economic Policy Research 33 Great Sutton Street, London EC1V 0DX, UK.
Bibliographic data for series maintained by CEPR ().