| NSF Org: |
SES Division of Social and Economic Sciences |
| Recipient: |
|
| Initial Amendment Date: | August 25, 2014 |
| Latest Amendment Date: | May 21, 2017 |
| Award Number: | 1343123 |
| Award Instrument: | Standard Grant |
| Program Manager: |
Brian Humes
SES Division of Social and Economic Sciences SBE Directorate for Social, Behavioral and Economic Sciences |
| Start Date: | September 1, 2014 |
| End Date: | August 31, 2019 (Estimated) |
| Total Intended Award Amount: | $2,594,533.00 |
| Total Awarded Amount to Date: | $2,594,533.00 |
| Funds Obligated to Date: |
|
| History of Investigator: |
|
| Recipient Sponsored Research Office: |
3112 LEE BUILDING COLLEGE PARK MD US 20742-5100 (301)405-6269 |
| Sponsor Congressional District: |
|
| Primary Place of Performance: |
8400 Baltimore Ave, Suite 250 College Park MD US 20740-2496 |
| Primary Place of
Performance Congressional District: |
|
| Unique Entity Identifier (UEI): |
|
| Parent UEI: |
|
| NSF Program(s): | INSPIRE |
| Primary Program Source: |
|
| Program Reference Code(s): |
|
| Program Element Code(s): |
|
| Award Agency Code: | 4900 |
| Fund Agency Code: | 4900 |
| Assistance Listing Number(s): | 47.075 |
ABSTRACT
This INSPIRE award brings together research areas typically supported by the Political Science Program of the Social and Economic Sciences Division of the Social, Behavioral, and Economic Sciences (SBE) Directorate; the Division of Information and Intelligent Systems and Office of Cyberinfrastructure of the Computer and Information Science and Engineering (CISE) Directorate; and the Division of Mathematical Sciences of the Mathematical and Physical Sciences (MPS) Directorate.
Although the relationship between grievances and political instability has concerned and fascinated policymakers and scientists for more than a century, prior research has been limited to comparative analysis of countries and a limited number of social surveys conducted within select countries. These traditional methods are expensive, labor intensive, and slow. A stark example of the weakness of traditional approaches are the events of the so-called "Arab Spring" which resulted in the outbreak of mass protests across North Africa and the Middle East; led to the overthrow of regimes in Egypt, Tunisia, and Libya; fomented a brutal and prolonged civil war in Syria; and triggered severe crack-downs in Bahrain. The Arab Spring caught both policymakers and academics by surprise, even though these events appear to have developed in large part out of grievances that built over decades of autocratic rule, widespread corruption and economic stagnation.
The main purpose of this research is to exploit the recent availability of worldwide, individual-level data from social media outlets such as Twitter and from the massive availability of worldwide news outlets to assess the possibility of measuring perceptions of grievances at the micro-level in real time for purposes of forecasting instability. It brings together researchers in computer science, mathematics, and the social sciences to generate theoretical and empirical advances. Hundreds of millions of people around the world are now using social media to communicate, making this technology-enabled forum a major de facto platform for political participation, expression, advocacy, and mobilization. In addition, the widespread availability of online news reports now offers the ability to collect content from newspapers and other print media worldwide and code for perceived grievances. By triangulating measures across social media, the news online, and traditional databases, the project evaluates their relative strength in terms of ascertaining and measuring grievances to forecast political instability. The overarching purpose of this research is to assist policymakers in developing improved methods for identifying and anticipating hot zones of instability and conflict. This has important implications for research but also for national policy, in terms of strategic thinking about defense, diplomacy, and humanitarian assistance, as well as in developing potential interventions and assessing their effectiveness once implemented.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
Our project had several goals including: (1) identifying and measuring grievances using traditional sources of data such as macroeconomic indicators, and more novel sources of data, including social media data; (2) using those indicators to evaluate their predictive or explanatory value for contentious activity and conflict; and (3) creating a replicable, transparent method enabling researchers to measure contentious activity and conflict, broadly defined. Our project succeeded in providing the following outcomes:
We developed a method using the no-cost Internet Archive's corpus of Tweets known as the 1% (or sprinkler sample) and compared empirical results to research on the full Twitter stream (or firehose). Our results showed that the 1% sample produced very similar results to the full Twitter stream for the applications tested.
We developed a method and coordinating package called MELLT (Matching Events by Location, Time, and Type) in the R programming language to integrate four different datasets on cross-national forms of political violence. We matched these events by comparing their location, date and time, and types of events, using a stable marriage algorithm. The MELLT data are now being used by researchers around the world and have the promise of making cross-national studies of the causes and consequences of political violence much more extensive and accurate than in the past.
We found considerable success in measuring negative sentiments in social media and linked them to various types of political violence, including terrorism. However, sentiment analysis through platforms like Twitter generally pick up negative sentiments after the event has already occurred rather than before the event. Given that the negative sentiments come after events like electoral violence, they are useful for examining the after effects of these types of political violence but are of less value in predicting the onset of political violence.
We found that social media can provide accurate measures of a wide range of standard social science data. This feature is especially useful for areas of the world where social data are scarce either because of low levels of technological development or areas that are conflict or war torn and difficult data collection locations. They may also be useful for collecting information on topics that respondents consider embarrassing or even criminal. However, we also found serious limitations in the applicability of social media data to a range of common social science issues. Moreover, social media data, like traditional media, most often provide insights in response to events. Thus, it is much easier to examine public sentiments toward terrorism or political violence following a specific terrorist attack than in general.
We found that in some circumstances social media data can be a useful tool in predicting the emergence of political instability. However, there are also important variations by specific type of politial instability.
Last Modified: 01/02/2020
Modified by: Gary Lafree
Please report errors in award information by writing to: awardsearch@nsf.gov.
