New study examines 20+ years of armed conflict data across Africa. Researchers @kushwaha.bsky.social and @spintheory.bsky.social identify three conflict archetypes, but also show that classification does not necessarily help to predict the severity of conflicts.
Learn more: shorturl.at/81pkf
🦋🧪 New research out in Royal Society Open Science! We used #MachineLearning to discover that armed #conflict in #Africa sorts into three distinct types—and found a surprising warning about predicting #violence. 🧵
@royalsociety.org
@csh.ac.at
@kushwaha
doi.org/10.1098/rsos...
With: @spintheory.bsky.social
we develop an empirical and bottom-up methodology to identify conflict types, knowledge of which can hurt predictability and cautions us about the limited utility of commonly available indicators. (6/6)
Specifying conflict type negatively impacts the predictability of conflict intensity such as fatalities, conflict duration, and other measures of conflict size. The competitive effect is a general consequence of weak statistical dependence. Hence, (5/6)
with little infrastructure and poor economic conditions. The three types stratify into a hierarchy of factors that highlights population, infrastructure, economics, and geography, respectively, as the most discriminative indicators. (4/6)
Local conflicts are in regions of median population density, are diverse socio-economically and geographically, and are often confined within country borders. Finally, sporadic and spillover conflicts remain small, often in low population density areas, (3/6)
we find three overarching conflict types representing "major unrest'' local conflict,'' and "sporadic and spillover events.'' Major unrest predominantly propagates around densely populated areas with well-developed infrastructure and flat, riparian geography. (2/6)
We combine fine-grained conflict data with detailed maps of climate, geography, infrastructure, economics, raw demographics, and demographic composition in Africa. With an unsupervised learning model, (1/6)
🚨New Research Alert🚨
Are commonly used indicators useful when predicting armed conflicts? Our latest study challenges conventional wisdom!
How many types of conflict exist according to data? And can we organize them into a meaningful hierarchical taxonomy?🦋💥
To find out:
arxiv.org/pdf/2503.00265
we develop an empirical and bottom-up methodology to identify conflict types, knowledge of which can hurt predictability and cautions us about the limited utility of commonly available indicators. (6/6)
Specifying conflict type negatively impacts the predictability of conflict intensity such as fatalities, conflict duration, and other measures of conflict size. The competitive effect is a general consequence of weak statistical dependence. Hence, (5/6)
with little infrastructure and poor economic conditions. The three types stratify into a hierarchy of factors that highlights population, infrastructure, economics, and geography, respectively, as the most discriminative indicators. (4/6)
Local conflicts are in regions of median population density, are diverse socio-economically and geographically, and are often confined within country borders. Finally, sporadic and spillover conflicts remain small, often in low population density areas, (3/6)
we find three overarching conflict types representing "major unrest'' local conflict,'' and "sporadic and spillover events.'' Major unrest predominantly propagates around densely populated areas with well-developed infrastructure and flat, riparian geography. (2/6)
We combine fine-grained conflict data with detailed maps of climate, geography, infrastructure, economics, raw demographics, and demographic composition in Africa. With an unsupervised learning model, (1/6)
What a whirlwind few months at CSH. But now we’re moved into our lovely new accommodations near Schloss Belvedere.
This week we have a student from our summer internship program Shlok Shah visiting us again from Princeton.
More science on armed conflict to come!
