Birth of a Revolution Pt. II — A global model for forecasting political instability

  1. The App : abhinayar.github.io/BirthOfARevolution
  2. Front-End Code : github.com/abhinayar/BirthOfARevolution
  3. Back-End Code : github.com/abhinayar/BirthOfARevolution_Backend

Introduction

Relevant Research

  1. Past historical analysis studies
  2. Past real-time analysis studies
  3. Historical ANOVA/Regression analysis research
  4. Implementation best practices

Historical Predictor

Sources

Building the model

  1. Inflation
  2. Youth Unemployment Rate
  3. Percent Urban Population
  4. Overall Globalization Rate
  5. Human Development Index
  6. Civil Liberties Index
  7. Corruption Perception Index
  8. Mobile Phone Use Per 100
  9. Literacy Rate
  10. Voice and Accountability Index
  11. Rule Of Law Index
  1. Inflation
  2. Youth Unemployment Rate
  3. Percent Urban Population
  4. Human Development Index
  5. Corruption Perception Index
  6. Mobile phone use per 100

Real-Time Predictor

  1. 7-day search based unrest estimation
  2. Real-time tweet stream sentiment aggregation
  3. GDELT realtime instability index

7-day Search Based Unrest Estimation

Real-time Tweet Stream Sentiment Aggregation

GDELT Realtime Stability Index

Combined Predictor

Results

  1. Streaming
  2. Search By Key Term
  3. Search By Country

Streaming

  1. Map the tweet on the globe with a marker indicating sentiment
  2. Post the tweet on the right sidebar
  3. Make a call to a REST API to receive country data and display it on the left side (for the country the tweet was from)
  4. Get the instability measure from our Firebase Real-time Database

Search By Key Term

Search By Country

Future Work

Conclusion

--

--

--

Just a dude who builds things on the internet. Hit me at abhi@tonebase.co.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

How to Create PowerBI HeatMap

A Name Across Time and Numbers

4 Business Intelligence And Analytics Best Practices: Fuel Your Brain, Save Time And Avoid Risk By…

How Couples Meet in the Age of the Internet

How couples meet, 1995 vs. 2017 according to survey data from heterosexual couples.

Ridge and Lasso Regression: L1 and L2 Regularization

The Dirty Little Secret Every Data Scientist Knows (but won’t admit)

Better maps for navigation

How to Lie with Statistics by Darrell Huff

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Abhi Nayar

Abhi Nayar

Just a dude who builds things on the internet. Hit me at abhi@tonebase.co.

More from Medium

Picking the right compression for high volume data transfer

The raw table definitions

Comparing performances of file formats in R: CSV to RDS, Parquet, and Feather

When the Data Isn’t Perfect

Swimming in the Data Lake