Papers

Linking Events and Locations in Political Text

(working paper) [pdf]

This work proposes the first general technique for automatically geolocating political events in text as one step in a broader project of recognizing political relationship and extracting political information from text. Using techniques borrowed from computational linguistics and a novel set of labeled sentences, I create an method to link events and locations in text that triples the accuracy of a reasonable baseline model. I describe the potential uses of such a system in political science, describe the neural-net based model, and demonstrate its ability to answer an open question on the role of conventional military offensives in causing civilian casualties in the Syrian civil war.

 

How Right Wing is Right Wing Populism? Evidence from the Manifesto Corpus

(working paper) [pdf]

Right wing populist parties in Europe are clearly different from other right wing parties in their rhetoric and electoral appeal. Some observers see substantive differences between right wing populists and other right wing parties, with populists supporting the welfare state and gender equality more than other right wing parties, often as part of an anti-immigration and anti-Muslim agenda. We test this claim using novel data produced by a multilingual convolutional neural net on political party platforms for the years 1990 to 2015 from the Manifesto Corpus. We find no systematic differences between right wing populists and non-populists on support for welfare and gender equality, though there is some evidence that more successful populists are more centrist.

Violence against civilians in Syria’s civil war

(working paper) [pdf]

I evaluate the ability of several competing theories of why armed groups kill civilians in civil war to explain violence in Syria. Using data on civilian deaths, territorial control, and military offensives geocoded to the town or village, I find much more support for a “drain the sea'” logic of civilian targeting than for theories emphasizing territorial control and intelligence. The paper develops two new quantitative methods: automatically geolocating Arabic place names and inferring degrees of territorial control from binary measures. These methods will aid future quantitative studies of civil war. 

 Posters

[pdf]

I develop a general technique for automatically geolocating political events in text Using techniques borrowed from computational linguistics and a novel set of labeled sentences, I create an method to link events and locations in text that greatly outperforms the accuracy of a reasonable baseline model. I describe the potential uses of such a system in political science, describe the neural-net based model, and demonstrate its ability to answer an open question on the role of conventional military offensives in causing civilian casualties in the Syrian civil war.

Advertisements