“Beating the news” with EMBERS: Forecasting Civil Unrest using Open Source Indicators thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

“Beating the news” with EMBERS: Forecasting Civil Unrest using Open Source Indicators

Published on Oct 07, 20142157 Views

We describe the design, implementation, and evaluation of EMBERS, an automated, 24x7 continuous system for forecasting civil unrest across 10 countries of Latin America using open source indicators su

Related categories

Chapter list

“Beating the news” with EMBERS: Forecasting Civil Unrest using Open Source Indicators00:00
The EMBERS Project00:06
The EMBERS team01:42
This paper02:28
Why forecast protests?03:30
How we get evaluated04:50
Lead time06:23
Other aspects of quality07:17
Matching alerts to events08:13
OSI Program Metrics08:42
EMBERS Architecture09:22
How we forecast civil unrest10:08
Audit Trail Interface12:35
How we did on the Brazilian Spring12:46
How we did in Venezuela’1413:09
Spread of protests (Venezuela’14)13:19
Future Work13:33