I Still Haven’t Found what I’m Looking for

Predicting Security-Related Incidents and Conflict Fatalities with Google Trends and Wikipedia Data

Bibliographic Data

ID10071595
AuthorsC Oswald (0000-0001-8291-9544, Universität der Bundeswehr München, corresponding author)
Year2025
Publication date2025-07-29
Peer ReviewedYes
Open AccessYes
TypeARTICLE
VenueJournal of Conflict Resolution (JOURNAL)
Journal identifiersISSN: 0022-0027 • E-ISSN: 1552-8766
PublisherSAGE Publishing (PUBLISHER • US)
DOI10.1177/00220027251362832
OpenAlexW4413098837
LanguageEN
Citations received1
References cited51

Conflict forecasting has seen two recent developments: a shift to predicting continuous variables and a debate about the value of structural and procedural variables. This paper contributes to these efforts and proposes the category of salience variables in the form of Google Trends and Wikipedia data. Internet searches can be precursors of conflict intensity as a result of for example an increase in protests, violent behavior, or public announcements. Data are readily and openly available, updated in real time, and provide global coverage which makes it ideal for near-real time forecasting. Prediction targets are the number of security-related incidents and battle-related, non-state, and civilian casualties. I demonstrate the value of salience variables using various out-of-sample windows and performance metrics on the country- and province-month level. I find evidence that salience variables have considerable predictive power, outperform other commonly used variables, and are thus a valuable addition to the conflict forecasting toolkit

Econometrics · Economics · Political science · Predictive power · Salience (neuroscience · Value (mathematics · Artificial Intelligence · Computer Science · COVID-19 epidemiological studies · Data-Driven Disease Surveillance · Terrorism, Counterterrorism, and Political Violence