Forecasting the Onset of Genocide and Politicide: Annual Out-of-Sample Forecasts on a Global Dataset, 1988-2003

What Drives State-Sponsored Violence?: Evidence from Extreme Bounds Analysis and Ensemble Learning Models

“…Our findings partially confirm previous research -unstable countries are more likely to witness the regime employ atrocity (e.g., Goldsmith et al 2013;Harff 2003;Krain 1997). …”

“…Does the logic underpinning government decision-making follow different patterns during peacetime and wartime? Recent research suggests that government atrocity occurs predominantly during periods of civil unrest (Harff 2003) which has led some scholars to restrict their analyses to only periods of civil war (e.g., Colaresi and Carey 2008;Valentino et al 2004) or concentrate on predicting both the onset of civil war and atrocity (Goldsmith et al 2013). Yet, others estimate models of all country-years (e.g., Krain 1997;Montalvo and Reynal-Querol 2008), raising questions of how well these studies speak to each other.…”

Triggers of Mass Atrocities

“…To date, there has been limited qualitative, comparative analysis of triggers of atrocity. In the quantitative literature on genocide, politicide, and mass killing, there has been analysis of "onset," which is different but akin to an analysis of triggers (Goldsmith et al, 2013;Harff, 2003;Ulfelder & Valentino, 2008;Uzonyi, 2015). Many of these studies point to underlying conditions that increase the probability of atrocity in a country, such as infant mortality, a general period of instability, authoritarianism, exclusionary ideologies, prior genocides, or ethnic cleavages.…”

“…In recent years, analysts have developed increasingly strong models for identifying risk factors of genocide and other mass atrocities, in particular concerning the macro-level drivers of such violence (Goldsmith, Butcher, Semenovich, & Sowmya, 2013;Ulfelder & Valentino, 2008; United Nations Office on Genocide Prevention and the Responsibility to Protect, 2014). 1 However, less is known about the specific timing of when atrocities will start and what will make them start.…”

Multi-level Analysis of Peace and Conflict Data in GDELT

“…Researchers are working towards harnessing these huge amounts of real-time information to obtain useful insights [27] and also use them as sources for predicting conflicts [29,30]. These noisy, near real-time streams of unstructured data starkly contrast the carefully selected and curated traditional peace and conflict databases.…”