Identification of peaceful and forceful collective action at NYC climate change protests in 2014 using streaming geo-coded Twitter data and an "adept" Bayes classifier (Anastasopoulos and Williams 2016).

I am Assistant Professor in the departments of Public Administration and Policy and Political Science at the University of Georgia and am excited to be one of the newest members of the Georgia Informatics Institute. Prior to joining the faculty at UGA I was a data science fellow at the UC Berkeley School of Information and  Democracy Fellow at the Harvard University John F. Kennedy School of Government. While a fellow at UC Berkeley, I had the pleasure of receiving training in computer vision and deep learning from Alexei Efros and Joan Bruna.

My substantive interests are in American Politics with a focus on bureaucracy, state, and local politics in the United States. My methods research interests include developing computational tools for dealing  with the idiosyncrasies of online experiments, Bayesian experimental design and analysis, machine learning methods for text and image analysis with a special interest in Bayesian nonparametrics, hierarchical Bayesian modeling of spatial data and stochastic optimization methods.

Copy and paste this code to your website.
Copy and paste this code to your website.

Substantive Interests

  • Political Economy
  • Political Behavior
  • Political Communication
  • Political Violence
  • The Politics of Migration and Immigration
  • Race and Ethnicity

Methodology Interests

  • Statistics of Causal Inference and Design of Experiments
  • Bayesian Inference
  • Machine Learning for Text and Image Analysis
  • Computer Vision
  • Scalable Stochastic Optimization
  • Spatial Data Visualization and Analysis