Format

Send to

Choose Destination
PLoS One. 2015 Jun 19;10(6):e0128879. doi: 10.1371/journal.pone.0128879. eCollection 2015.

Forecasting Social Unrest Using Activity Cascades.

Author information

1
Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA; Department of Computer Science, Virginia Tech, Blacksburg, VA, USA.
2
Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA.
3
Virginia Bioinformatics Institute, Virginia Tech, Blacksburg, VA, USA; Department of Agricultural and Applied Economics, Virginia Tech, Blacksburg, VA, USA.
4
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA.

Abstract

Social unrest is endemic in many societies, and recent news has drawn attention to happenings in Latin America, the Middle East, and Eastern Europe. Civilian populations mobilize, sometimes spontaneously and sometimes in an organized manner, to raise awareness of key issues or to demand changes in governing or other organizational structures. It is of key interest to social scientists and policy makers to forecast civil unrest using indicators observed on media such as Twitter, news, and blogs. We present an event forecasting model using a notion of activity cascades in Twitter (proposed by Gonzalez-Bailon et al., 2011) to predict the occurrence of protests in three countries of Latin America: Brazil, Mexico, and Venezuela. The basic assumption is that the emergence of a suitably detected activity cascade is a precursor or a surrogate to a real protest event that will happen "on the ground." Our model supports the theoretical characterization of large cascades using spectral properties and uses properties of detected cascades to forecast events. Experimental results on many datasets, including the recent June 2013 protests in Brazil, demonstrate the effectiveness of our approach.

PMID:
26091012
PMCID:
PMC4474666
DOI:
10.1371/journal.pone.0128879
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Public Library of Science Icon for PubMed Central
Loading ...
Support Center