Planned Protest Modeling in News and Social Media

Civil unrest (protests, strikes, and “occupy ” events) is a common occurrence in both democracies and au-thoritarian regimes. The study of civil unrest is a key topic for political scientists as it helps capture an im-portant mechanism by which citizenry express them-selves. In countries where civil unrest is lawful, qual-itative analysis has revealed that more than 75 % of the protests are planned, organized, and/or announced in advance; therefore detecting future time mentions in rel-evant news and social media is a direct way to develop a protest forecasting system. We develop such a system in this paper, using a combination of key phrase learning to identify what to look for, probabilistic soft logic to rea-son about location occurrences in extracted results, and time normalization to resolve future tense mentions. We illustrate the application of our system to 10 countries i