SlideShare a Scribd company logo
1 of 17
Forecasting Country Stability in 
North Africa 
V.S. Subrahmanian (UMD + Sentimetrix) 
vs@sentimetrix.com 
Joint work with 
Steven Banaszak (Sentimetrix) 
Liz Bowman (US Army) 
John Dickerson (CMU + Sentimetrix) 
Sentimetrix - JISIC, The Hague, Sep 2014 1
Research Goal 
Can we accurately predict various stability 
related events in North Africa (Egypt, 
Morocco, Sudan) by mining sentiment in 
open source data on various key players, 
even with a relative paucity of longitudinal 
data (36 time points)? 
Sentimetrix - JISIC, The Hague, Sep 2014 2
Research Goal 
• Provide a single dashboard that will enable an 
analyst to 
– See international stability situation at a glance 
– Focus on countries of interest to him 
– Look at forecasts in countries of interest to him 
– Understand the rationale for the forecasts 
– Understand the “why” around those forecasts 
– Understand relationship between sentiment on 
different entities and stability events in countries 
• This study focuses on Egypt, Morocco, and Sudan. 
Sentimetrix - JISIC, The Hague, Sep 2014 3
SentiBility Architecture 
Sentimetrix - JISIC, The Hague, Sep 2014 4
Dependent Variables 
• The current SentiBility (SB) system has 5 DVs: 
– Battles (did government engage in battles?) 
– WonBattles (did gov win territory) 
– LostBattles (did gov lose battles) 
– Riots/Protests (were there riots and/or protests?) 
– Violence Against Civilians 
• These are the phenomena we are trying to 
predict. 
• Historical data on DVs collected using ACCLED 
data set from University of Sussex for 36 months. 
Sentimetrix - JISIC, The Hague, Sep 2014 5
Independent Variables: Data 
• Political Entity Dataset (PED): set of key political leaders, 
parties, opposition groups, for each country. 
• Hybrid Article Dataset (HAD): For each entity in PED, 
identified a set of articles (blog posts, news, tweets, 
forums) that reference that entity. 
• Open-Source Sentiment DB: Assigns a score in [-1,+1] to 
each article-entity pair, specifying sentiment score of entity 
in the article. 
– -1 denotes maximally negative score 
– +1 shows maximally positive score 
– 0 is completely neutral 
• Data about IVs was collected for 2-3 years varying by 
country during the 2008-2011 time frame. 
Sentimetrix - JISIC, The Hague, Sep 2014 6
Sentiment Scoring 
Used Sentimetrix’s Sentiment Scoring Engine which leverages 
many past papers by us: 
• V.S. Subrahmanian et al. US Patent US 8296168 B2 System 
and method for analysis of an opinion expressed in 
documents with regard to a particular topic, Priority date 
Sep 13 2006 
• Subrahmanian, V. S., and Diego Reforgiato. "AVA: Adjective-verb- 
adverb combinations for sentiment analysis." IEEE 
Intelligent Systems, 23.4 (2008): 43-50. 
• Cesarano, Carmine, et al. "Opinion Analysis in Document 
Databases." AAAI Spring Symposium: Computational 
Approaches to Analyzing Weblogs. 2006. 
Sentimetrix - JISIC, The Hague, Sep 2014 7
Learning Classifiers 
• Training/validation set was an approximately 70/30 split. 
• Applied an ensemble of 5 classifier families 
– Gaussian NB 
– Support Vector Machines 
– Random forests 
– AdaBoost 
– GradientBoost 
• Each classifier family was optimized using leave-one-out 
cross validation via a hyper-parameter grid search to find 
best parameters. 
• Different classifier families were best for different 
predictions (country-event). 
Sentimetrix - JISIC, The Hague, Sep 2014 8
Egypt Case Study 
• PED contained 55 Egyptian entities. 
Sentimetrix - JISIC, The Hague, Sep 2014 9
Egypt Case Study 
• High sentiment on Adel Labib inversely correlated with 
violence against civilians. 
• High sentiment on Ahmed Ghanem inversely correlated with 
riots/protests. 
• When sentiment on Morso, El-Baradei, and Tantawi were all 
high, then there were few battles. 
Sentimetrix - JISIC, The Hague, Sep 2014 10
Egypt Case Study: 
Multivariate Forecast Accuracy 
Dependent Variable Forecast Accuracy 
Battle 72% 
Violence against Civilians 90% 
Riots and Protests 90% 
Sentimetrix - JISIC, The Hague, Sep 2014 11
Sudan Case Study 
• PED contained 88 Sudanese entities. 
Sentimetrix - JISIC, The Hague, Sep 2014 12
Sudan Case Study: 
Multivariate Forecast Accuracy 
Dependent Variable Forecast Accuracy 
Won-Battle 69% 
Riots and Protests 88% 
Sentimetrix - JISIC, The Hague, Sep 2014 13
System Screenshots 
Sentimetrix - JISIC, The Hague, Sep 2014 14
System Screenshots 
Sentimetrix - JISIC, The Hague, Sep 2014 15
System Screenshots 
Sentimetrix - JISIC, The Hague, Sep 2014 16
Contact Information 
V.S. Subrahmanian 
Founder 
Sentimetrix, Inc. 
vs@sentimetrix.com 
@vssubrah 
www.sentimetrix.com 
Sentimetrix - JISIC, The Hague, Sep 2014 17

More Related Content

Similar to Stability north-africa-jisic-2014

Data Governance in two different data archives: When is a federal data reposi...
Data Governance in two different data archives: When is a federal data reposi...Data Governance in two different data archives: When is a federal data reposi...
Data Governance in two different data archives: When is a federal data reposi...Carolyn Ten Holter
 
Wikistrat-Executive-Summary-2015
Wikistrat-Executive-Summary-2015Wikistrat-Executive-Summary-2015
Wikistrat-Executive-Summary-2015Esa K. Vierikko
 
Forecasting Elections from Voters’ Perceptions
Forecasting Elections from Voters’ Perceptions Forecasting Elections from Voters’ Perceptions
Forecasting Elections from Voters’ Perceptions agraefe
 
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...Parang Saraf
 
Big Data @ CBS for Fontys students in Eindhoven
Big Data @ CBS for Fontys students in EindhovenBig Data @ CBS for Fontys students in Eindhoven
Big Data @ CBS for Fontys students in EindhovenPiet J.H. Daas
 
RapidMiner, an entrance to explore MIMIC-III?
RapidMiner, an entrance to explore MIMIC-III?RapidMiner, an entrance to explore MIMIC-III?
RapidMiner, an entrance to explore MIMIC-III?Sven Van Poucke, MD, PhD
 
Stock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisStock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisjournal ijrtem
 
Stock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisStock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisIJRTEMJOURNAL
 
These slides cover the final defense presentation for my Doctorate degree. Th...
These slides cover the final defense presentation for my Doctorate degree. Th...These slides cover the final defense presentation for my Doctorate degree. Th...
These slides cover the final defense presentation for my Doctorate degree. Th...Eric Brown
 
Rand rr2539z2.appendix b
Rand rr2539z2.appendix bRand rr2539z2.appendix b
Rand rr2539z2.appendix bBookStoreLib
 
Researchers are from Venus, policy makers from Mars
Researchers are from Venus, policy makers from MarsResearchers are from Venus, policy makers from Mars
Researchers are from Venus, policy makers from Marswellcome.trust
 
Demand analysis ppt bec bagalkot mba
Demand analysis ppt bec bagalkot mbaDemand analysis ppt bec bagalkot mba
Demand analysis ppt bec bagalkot mbaBabasab Patil
 
Internship_project_report.docx
Internship_project_report.docxInternship_project_report.docx
Internship_project_report.docxAnujaDekate
 
HLEG thematic workshop on Measuring Trust and Social Capital, Yann Algan
HLEG thematic workshop on Measuring Trust and Social Capital, Yann AlganHLEG thematic workshop on Measuring Trust and Social Capital, Yann Algan
HLEG thematic workshop on Measuring Trust and Social Capital, Yann AlganStatsCommunications
 
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...HFG Project
 
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...NAP Global Network
 

Similar to Stability north-africa-jisic-2014 (20)

Data Governance in two different data archives: When is a federal data reposi...
Data Governance in two different data archives: When is a federal data reposi...Data Governance in two different data archives: When is a federal data reposi...
Data Governance in two different data archives: When is a federal data reposi...
 
Wikistrat-Executive-Summary-2015
Wikistrat-Executive-Summary-2015Wikistrat-Executive-Summary-2015
Wikistrat-Executive-Summary-2015
 
Forecasting Elections from Voters’ Perceptions
Forecasting Elections from Voters’ Perceptions Forecasting Elections from Voters’ Perceptions
Forecasting Elections from Voters’ Perceptions
 
Python term project
Python term projectPython term project
Python term project
 
Gender-Responsive Age-Sensitive Social Protection (GRASSP)
Gender-Responsive Age-Sensitive Social Protection (GRASSP)Gender-Responsive Age-Sensitive Social Protection (GRASSP)
Gender-Responsive Age-Sensitive Social Protection (GRASSP)
 
Tim Midgley, Saferworld (UK )
Tim Midgley, Saferworld (UK )Tim Midgley, Saferworld (UK )
Tim Midgley, Saferworld (UK )
 
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...
‘Beating the News’ with EMBERS: Forecasting Civil Unrest using Open Source In...
 
ICCM 2014 -- Ignite Talks -- Session 2
ICCM 2014 -- Ignite Talks -- Session 2ICCM 2014 -- Ignite Talks -- Session 2
ICCM 2014 -- Ignite Talks -- Session 2
 
Big Data @ CBS for Fontys students in Eindhoven
Big Data @ CBS for Fontys students in EindhovenBig Data @ CBS for Fontys students in Eindhoven
Big Data @ CBS for Fontys students in Eindhoven
 
RapidMiner, an entrance to explore MIMIC-III?
RapidMiner, an entrance to explore MIMIC-III?RapidMiner, an entrance to explore MIMIC-III?
RapidMiner, an entrance to explore MIMIC-III?
 
Stock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisStock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysis
 
Stock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysisStock market prediction using Twitter sentiment analysis
Stock market prediction using Twitter sentiment analysis
 
These slides cover the final defense presentation for my Doctorate degree. Th...
These slides cover the final defense presentation for my Doctorate degree. Th...These slides cover the final defense presentation for my Doctorate degree. Th...
These slides cover the final defense presentation for my Doctorate degree. Th...
 
Rand rr2539z2.appendix b
Rand rr2539z2.appendix bRand rr2539z2.appendix b
Rand rr2539z2.appendix b
 
Researchers are from Venus, policy makers from Mars
Researchers are from Venus, policy makers from MarsResearchers are from Venus, policy makers from Mars
Researchers are from Venus, policy makers from Mars
 
Demand analysis ppt bec bagalkot mba
Demand analysis ppt bec bagalkot mbaDemand analysis ppt bec bagalkot mba
Demand analysis ppt bec bagalkot mba
 
Internship_project_report.docx
Internship_project_report.docxInternship_project_report.docx
Internship_project_report.docx
 
HLEG thematic workshop on Measuring Trust and Social Capital, Yann Algan
HLEG thematic workshop on Measuring Trust and Social Capital, Yann AlganHLEG thematic workshop on Measuring Trust and Social Capital, Yann Algan
HLEG thematic workshop on Measuring Trust and Social Capital, Yann Algan
 
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...
How Do Countries Use Resource Tracking Data to Inform Policy Change: Shining ...
 
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...
Measuring Progress: Indicators, Data Sources and Assessment | Laszlo Pinter, ...
 

Recently uploaded

Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationSérgio Sacani
 
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...Cherry
 
Cyanide resistant respiration pathway.pptx
Cyanide resistant respiration pathway.pptxCyanide resistant respiration pathway.pptx
Cyanide resistant respiration pathway.pptxCherry
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCherry
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceAlex Henderson
 
Concept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdfConcept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdfCherry
 
Porella : features, morphology, anatomy, reproduction etc.
Porella : features, morphology, anatomy, reproduction etc.Porella : features, morphology, anatomy, reproduction etc.
Porella : features, morphology, anatomy, reproduction etc.Cherry
 
FS P2 COMBO MSTA LAST PUSH past exam papers.
FS P2 COMBO MSTA LAST PUSH past exam papers.FS P2 COMBO MSTA LAST PUSH past exam papers.
FS P2 COMBO MSTA LAST PUSH past exam papers.takadzanijustinmaime
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Cherry
 
GBSN - Biochemistry (Unit 3) Metabolism
GBSN - Biochemistry (Unit 3) MetabolismGBSN - Biochemistry (Unit 3) Metabolism
GBSN - Biochemistry (Unit 3) MetabolismAreesha Ahmad
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusNazaninKarimi6
 
Plasmid: types, structure and functions.
Plasmid: types, structure and functions.Plasmid: types, structure and functions.
Plasmid: types, structure and functions.Cherry
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professormuralinath2
 
Understanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution MethodsUnderstanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution Methodsimroshankoirala
 
Daily Lesson Log in Science 9 Fourth Quarter Physics
Daily Lesson Log in Science 9 Fourth Quarter PhysicsDaily Lesson Log in Science 9 Fourth Quarter Physics
Daily Lesson Log in Science 9 Fourth Quarter PhysicsWILSONROMA4
 
Role of AI in seed science Predictive modelling and Beyond.pptx
Role of AI in seed science  Predictive modelling and  Beyond.pptxRole of AI in seed science  Predictive modelling and  Beyond.pptx
Role of AI in seed science Predictive modelling and Beyond.pptxArvind Kumar
 
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...Cherry
 
Lipids: types, structure and important functions.
Lipids: types, structure and important functions.Lipids: types, structure and important functions.
Lipids: types, structure and important functions.Cherry
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Cherry
 

Recently uploaded (20)

Efficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence accelerationEfficient spin-up of Earth System Models usingsequence acceleration
Efficient spin-up of Earth System Models usingsequence acceleration
 
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...
Major groups of bacteria: Spirochetes, Chlamydia, Rickettsia, nanobes, mycopl...
 
Cyanide resistant respiration pathway.pptx
Cyanide resistant respiration pathway.pptxCyanide resistant respiration pathway.pptx
Cyanide resistant respiration pathway.pptx
 
CYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptxCYTOGENETIC MAP................ ppt.pptx
CYTOGENETIC MAP................ ppt.pptx
 
FAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical ScienceFAIRSpectra - Enabling the FAIRification of Analytical Science
FAIRSpectra - Enabling the FAIRification of Analytical Science
 
Concept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdfConcept of gene and Complementation test.pdf
Concept of gene and Complementation test.pdf
 
ABHISHEK ANTIBIOTICS PPT MICROBIOLOGY // USES OF ANTIOBIOTICS TYPES OF ANTIB...
ABHISHEK ANTIBIOTICS PPT MICROBIOLOGY  // USES OF ANTIOBIOTICS TYPES OF ANTIB...ABHISHEK ANTIBIOTICS PPT MICROBIOLOGY  // USES OF ANTIOBIOTICS TYPES OF ANTIB...
ABHISHEK ANTIBIOTICS PPT MICROBIOLOGY // USES OF ANTIOBIOTICS TYPES OF ANTIB...
 
Porella : features, morphology, anatomy, reproduction etc.
Porella : features, morphology, anatomy, reproduction etc.Porella : features, morphology, anatomy, reproduction etc.
Porella : features, morphology, anatomy, reproduction etc.
 
FS P2 COMBO MSTA LAST PUSH past exam papers.
FS P2 COMBO MSTA LAST PUSH past exam papers.FS P2 COMBO MSTA LAST PUSH past exam papers.
FS P2 COMBO MSTA LAST PUSH past exam papers.
 
Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.Reboulia: features, anatomy, morphology etc.
Reboulia: features, anatomy, morphology etc.
 
GBSN - Biochemistry (Unit 3) Metabolism
GBSN - Biochemistry (Unit 3) MetabolismGBSN - Biochemistry (Unit 3) Metabolism
GBSN - Biochemistry (Unit 3) Metabolism
 
development of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virusdevelopment of diagnostic enzyme assay to detect leuser virus
development of diagnostic enzyme assay to detect leuser virus
 
Plasmid: types, structure and functions.
Plasmid: types, structure and functions.Plasmid: types, structure and functions.
Plasmid: types, structure and functions.
 
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate ProfessorThyroid Physiology_Dr.E. Muralinath_ Associate Professor
Thyroid Physiology_Dr.E. Muralinath_ Associate Professor
 
Understanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution MethodsUnderstanding Partial Differential Equations: Types and Solution Methods
Understanding Partial Differential Equations: Types and Solution Methods
 
Daily Lesson Log in Science 9 Fourth Quarter Physics
Daily Lesson Log in Science 9 Fourth Quarter PhysicsDaily Lesson Log in Science 9 Fourth Quarter Physics
Daily Lesson Log in Science 9 Fourth Quarter Physics
 
Role of AI in seed science Predictive modelling and Beyond.pptx
Role of AI in seed science  Predictive modelling and  Beyond.pptxRole of AI in seed science  Predictive modelling and  Beyond.pptx
Role of AI in seed science Predictive modelling and Beyond.pptx
 
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...
Molecular phylogeny, molecular clock hypothesis, molecular evolution, kimuras...
 
Lipids: types, structure and important functions.
Lipids: types, structure and important functions.Lipids: types, structure and important functions.
Lipids: types, structure and important functions.
 
Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.Phenolics: types, biosynthesis and functions.
Phenolics: types, biosynthesis and functions.
 

Stability north-africa-jisic-2014

  • 1. Forecasting Country Stability in North Africa V.S. Subrahmanian (UMD + Sentimetrix) vs@sentimetrix.com Joint work with Steven Banaszak (Sentimetrix) Liz Bowman (US Army) John Dickerson (CMU + Sentimetrix) Sentimetrix - JISIC, The Hague, Sep 2014 1
  • 2. Research Goal Can we accurately predict various stability related events in North Africa (Egypt, Morocco, Sudan) by mining sentiment in open source data on various key players, even with a relative paucity of longitudinal data (36 time points)? Sentimetrix - JISIC, The Hague, Sep 2014 2
  • 3. Research Goal • Provide a single dashboard that will enable an analyst to – See international stability situation at a glance – Focus on countries of interest to him – Look at forecasts in countries of interest to him – Understand the rationale for the forecasts – Understand the “why” around those forecasts – Understand relationship between sentiment on different entities and stability events in countries • This study focuses on Egypt, Morocco, and Sudan. Sentimetrix - JISIC, The Hague, Sep 2014 3
  • 4. SentiBility Architecture Sentimetrix - JISIC, The Hague, Sep 2014 4
  • 5. Dependent Variables • The current SentiBility (SB) system has 5 DVs: – Battles (did government engage in battles?) – WonBattles (did gov win territory) – LostBattles (did gov lose battles) – Riots/Protests (were there riots and/or protests?) – Violence Against Civilians • These are the phenomena we are trying to predict. • Historical data on DVs collected using ACCLED data set from University of Sussex for 36 months. Sentimetrix - JISIC, The Hague, Sep 2014 5
  • 6. Independent Variables: Data • Political Entity Dataset (PED): set of key political leaders, parties, opposition groups, for each country. • Hybrid Article Dataset (HAD): For each entity in PED, identified a set of articles (blog posts, news, tweets, forums) that reference that entity. • Open-Source Sentiment DB: Assigns a score in [-1,+1] to each article-entity pair, specifying sentiment score of entity in the article. – -1 denotes maximally negative score – +1 shows maximally positive score – 0 is completely neutral • Data about IVs was collected for 2-3 years varying by country during the 2008-2011 time frame. Sentimetrix - JISIC, The Hague, Sep 2014 6
  • 7. Sentiment Scoring Used Sentimetrix’s Sentiment Scoring Engine which leverages many past papers by us: • V.S. Subrahmanian et al. US Patent US 8296168 B2 System and method for analysis of an opinion expressed in documents with regard to a particular topic, Priority date Sep 13 2006 • Subrahmanian, V. S., and Diego Reforgiato. "AVA: Adjective-verb- adverb combinations for sentiment analysis." IEEE Intelligent Systems, 23.4 (2008): 43-50. • Cesarano, Carmine, et al. "Opinion Analysis in Document Databases." AAAI Spring Symposium: Computational Approaches to Analyzing Weblogs. 2006. Sentimetrix - JISIC, The Hague, Sep 2014 7
  • 8. Learning Classifiers • Training/validation set was an approximately 70/30 split. • Applied an ensemble of 5 classifier families – Gaussian NB – Support Vector Machines – Random forests – AdaBoost – GradientBoost • Each classifier family was optimized using leave-one-out cross validation via a hyper-parameter grid search to find best parameters. • Different classifier families were best for different predictions (country-event). Sentimetrix - JISIC, The Hague, Sep 2014 8
  • 9. Egypt Case Study • PED contained 55 Egyptian entities. Sentimetrix - JISIC, The Hague, Sep 2014 9
  • 10. Egypt Case Study • High sentiment on Adel Labib inversely correlated with violence against civilians. • High sentiment on Ahmed Ghanem inversely correlated with riots/protests. • When sentiment on Morso, El-Baradei, and Tantawi were all high, then there were few battles. Sentimetrix - JISIC, The Hague, Sep 2014 10
  • 11. Egypt Case Study: Multivariate Forecast Accuracy Dependent Variable Forecast Accuracy Battle 72% Violence against Civilians 90% Riots and Protests 90% Sentimetrix - JISIC, The Hague, Sep 2014 11
  • 12. Sudan Case Study • PED contained 88 Sudanese entities. Sentimetrix - JISIC, The Hague, Sep 2014 12
  • 13. Sudan Case Study: Multivariate Forecast Accuracy Dependent Variable Forecast Accuracy Won-Battle 69% Riots and Protests 88% Sentimetrix - JISIC, The Hague, Sep 2014 13
  • 14. System Screenshots Sentimetrix - JISIC, The Hague, Sep 2014 14
  • 15. System Screenshots Sentimetrix - JISIC, The Hague, Sep 2014 15
  • 16. System Screenshots Sentimetrix - JISIC, The Hague, Sep 2014 16
  • 17. Contact Information V.S. Subrahmanian Founder Sentimetrix, Inc. vs@sentimetrix.com @vssubrah www.sentimetrix.com Sentimetrix - JISIC, The Hague, Sep 2014 17