Forecasting Political Instability Using Heterogeneous Data Streams

• Activity Number: 320 - Statistical Approaches for Modeling Social Unrests
• Type: Invited
• Date/Time: Tuesday, July 30, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Defense and National Security
• Author(s): Chrysm Watson Ross* and Ashlynn Daughton and Geoffrey Fairchild and Sara Del Valle
• Companies: Los Alamos National Laboratory and Los Alamos National Laboratory and Los Alamos National Laboratory and Los Alamos National Laboratory
• Keywords: Political instability; Big-data; Forecasting; Disparate data streams

Abstract

Globalization has created complex socioeconomic and political problems that can no longer be adequately analyzed using traditional techniques and data sources. Whether the goal is to monitor the emergence of a new terrorist organization, societal changes initiated by a viral tweet, or rogue nation actions being subtly observed by citizenry, there are near-real-time digital signatures associated with the disruptive event. Thus, there is a need for new approaches that leverage nontraditional data streams to produce actionable and timely decision support. In this talk, I will describe an approach that combines heterogeneous data streams, such as tweets and news sources, to extract sentiment around particular events to ultimately forecast instability. This work is an important first step for improving decision support by assimilating real-time information into models to predict political instability at a global scale.