Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Social Media Prediction for Political Unrest

No description
by

Usamah Algemili

on 26 December 2013

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Social Media Prediction for Political Unrest

Social Media Prediction for Political Unrest
Usamah Algemili
Web Data Expl & Analytics
GWU CS Fall 2013

Tools and Techniques
1- Scientific Research.

2- Science Journals (Information-Communication Technology).

3- Web-based Applications.
Scope
Technical Challenges
Twitter API v1 is retired. Jun 2013
Suggested Model
1- Track historical data in social networks depending on word frequency.

2- Select word phrase according to targeted region/language.

2- keep track any deviations from average frequency.
Conclusions
- Political and Economic Indexes are not sufficient triggers to predict unrest accurately.

- Social Networks and Internet-based Media present an adequate measures for social behavior changes.

- For better results, word choice should rely on the targeted region, culture and language.

- Despite the fact that Social Network may not the main drive for political unrest, Social Networks played an important role in forming these revolutions.
Motivation
In early 2011, mass protests swept through the Middle East.
Social media networks played an important role in this political change -known as “Arabic Spring”-.
1- Survey the previous work on this topic.

2- Evaluate the accuracy of Social Media’s forecasts and predictions.
.
3- Attempt to conclude whether the current analysis is adequate enough forming proactive and informative decisions.

Contradictions
A. Some journalists have reported these revolutions as “Facebook Revelation” or “Twitter Revaluation”.
B. political analysts believe that Social Media’s role in Arabic Spring has been exaggerated.
They suggest that political unrest is driven by sociopolitical and socioeconomic factors.
Web-based Applications
Previous Work
- SUPERCOMPUTER PREDICTS

Kalev Leetaru at the University of Illinois’ Institute for Computing in the Humanities, Arts and Social Science. Sep 2011
- NETWORK THEORY AND POLITICAL REVOLUTION.

Carrie O‟Connell
San Diego State University
Journalism and Media Studies
- Political Unrest Index
The Atlantic
RICHARD FLORIDA
MAR 1 2011
Third Party Services Affected.
Twitter limits API calls from a single IP address at approved ("whitelisted") Twitter services to 20,000 per hour.
SUPERCOMPUTER PREDICTS
Data source:
Capturing the global news discourse.
Method:
Text mining and analytics.
Conclusion:
1-global news monitoring is now derived from Internet–based news.
2-this model can accurately forecast near–term stability.
Political Unrest Index
Data source:
1- Age structure of the population.
2- Number of years a government has been in power.
3- Democracy Index.
4- Corruption Index.
5- GDP per person.
Method:
Create Index of Potential Unrest (IPU).
Conclusion:
The results do not represent informative index.
Future Work
- Define process that selects trigger-words among different languages. e.g buzz words. Then store them in track list.
- Implement application that track word list averages.
- develop notification process for unusual word frequency.
Full transcript