Analyzing conflicts and political violence around the world is a persistent challenge in the political science and policy communities due in large part to the vast volumes of specialized text needed to monitor conflict and violence on a global scale.
To help advance research in political science, we introduce ConfliBERT, a domain-specific pre-trained language model for conflict and political violence.
We first gather a large domain-specific text corpus for language modeling from various sources. We then build ConfliBERT using two approaches: pre-training from scratch and continual pre-training.
To evaluate ConfliBERT, we collect 12 datasets and implement 18 tasks to assess the models’ practical application in conflict research. Finally, we evaluate several versions of ConfliBERT in multiple experiments.
Results consistently show that ConfliBERT outperforms BERT when analyzing political violence and conflict.
Access the code and replication materials here.
Eventus ID is a supervised coding protocol for automated identification of event data based on pattern recognition of textual information written in Spanish.
Eventus ID helps to provide a detailed account on who did what to whom, when and where.
Eventus ID is the product of a collaborative work between Javier Osorio and Alejandro Reyes, with support of the National Science Foundation [SES-1123572]; the Jennings Randolph Peace Scholar fellowship of the United States Institute for Peace; and the Drugs Security and Democracy fellowship of the Social Science Research Council - Open Society Foundations.
Web Text Downloader
School of Government and Public Policy
University of Arizona