Hello, My name is Rebecca Abbott and I am a PhD candidate in the Sociology department of the University of Illinois at Chicago. I'm completing my dissertation using machine learning methods (in R) to predict mass atrocities. I currently teach the graduate statistics lab, helping students model their own projects using Stata. My strongest skills are model building, statistics and data analysis. My areas of research are primarily focused on economic policy, inequality, racial attitudes and group violence. Current research projects include: -Time series analysis on racial attitudes of Black, White and Hispanic Americans controlling for the individual’s economic hardship during the 2007 recession. The purpose of this project is to understand how economic conditions affect racial attitudes. This was done in Stata using multiple years of the General Social Survey paired with data from the US Census Bureau. -Using logistic regression and Hierarchical Linear Modeling to predict voting behavior in the 2016 election using county history of racialized voting and lynching violence. The data came from historical records of lynching, U.S. census data, and county cluster data created by Dr. Amy Bailey of U.I.C. -Fuzzy set-Qualitative Comparative Analysis on national level datasets measuring economic variables to find necessary and sufficient conditions for mass atrocities. The data was from multiple sources (U.N., World Bank, PITF) stored as rich text files and converted to spreadsheet stored on GitHub from multiple data sources. -Cluster analysis and random forests to predict likelihood of mass atrocities using economic and social policy measures. Data is from multiple data sources (World Bank, CIA, UN, WHO, WTO) data is in text format and stored on GitHub. Much of this work has been done for academic publishing but I am currently trying to shift gears toward producing work for a public audience. My goal here is to get more experience and do good work.

Personal information
Full name: Rebecca Abbott
User name: reabbot
Organization memberships
MedicMobile (Staff)
First 1000 volunteers
Volunteer background
Education: Master's on Measurement Evaluation and Statistical Assessment (University of Illinois at Chicago)
Volunteer availability
Start date: June 17, 2020
End date: None
Hours available per week: 15
Volunteering interests
No stated preferences.
Computer Science (Algorithms)
Data in Text Files
Text Data (NLP)
Social Science (Economics, Sociology, etc.)
Experimental Methods (RCTs, A/B testing, etc.)
Experience working on real-world problems using data
Data Visualization
Data Analysis
Decision Trees
Random Forests
Causal inference
Neural Networks / Deep Learning
Time Series Models
Unsupervised models
Semi-Supervised models
Regression Discontinuity
Instrumental Variables
Matching (e.g., Propensity Score Matching )

Volunteer projects

Project name Organization name Social impact area Project summary Task name Task status
Community Vulnerability Index Community Insight and Impact Education Data driven assessment of community needs across multiple axes; currently focused on COVID-19 but will be useful for other pandemics or disasters. Project scoping Started
Identifying economic and financial incentives for forest and landscape restoration in Latin America using Natural Language Processing World Resources Institute Education Forest and landscape restoration is a cross-cutting agenda that traverses sectors such as agriculture, forestry, water and natural resources. While this cross-cutting nature makes restoration an attractive policy measure for carbon sequestration, mitigation, and adaptation, it complicates policy analysis. The sheer volume of text impedes researchers and decision makers from identifying misalignment and monitoring evolving policy and agenda shifts. Analyzing such a large corpus of documents exacerbates policy analysis’ transparency, objectivity, access, and scalability. Our proposal is to standardize and scale policy analysis, alignment, and agenda setting with natural language processing (NLP). A previous proof-of-concept we developed demonstrated the utility of NLP to quickly summarize agenda-specific information from policies. The aim of this project would be to identify financial and economic incentives to support enabling conditions for Nature Based Solutions. Project scoping Started