Patrick T. Brandt

Patrick T. Brandt

Professor of Political Science

My political science research employs time series analysis methods and machine learning in a variety of areas to study change in economic and political events.

Tags: Political Science Social Data Analytics and Research Political Economy

Professional Preparation

Ph.D. - Political Science
Indiana University - 2001
M.S. - Mathematical Methods in Social Sciences
Northwestern University, - 1997
A.B. - Government
College of William and Mary, Williamsburg - 1994

Research Areas

Research Interests

My research on political and social dynamics focuses on the development and application of time series models to forecast international relations, to explicate relationships among public opinion, economic policy and the economy, and to explain patterns of conflict and terrorism. The main time series models employed in this research involve Bayesian statistics, multiple equation or vector autoregression models, methods for producing and evaluating the quality of forecasts, the derivation of new models for time series of counts, and modeling structural change and endogenous shifts in data over time.

This research agenda has been funded by the National Science Foundation and the Center for Economic and Risk Analysis of Terrorist Events (CREATE)

Publications

Conflict forecasting with event data and spatio-temporal graph convolutional networks 2022 - Journal Article
Conflict forecasting with event data and spatio-temporal graph convolutional networks 2022 - Journal Article
An Online Structured Political Event Dataset based on CAMEO Ontology 2020 - Other
An Online Structured Political Event Dataset based on CAMEO Ontology 2020 - Other
UTDEventData: An R package to access political event data 2019 - Journal Article
UTDEventData: An R package to access political event data 2019 - Journal Article
APART: Automatic Political Actor Recommendation in Real-time 2017 - Book Chapter
APART: Automatic Political Actor Recommendation in Real-time 2017 - Book Chapter

Appointments

Professor
University of Texas at Dallas [2015–Present]
Associate Professor
University of Texas at Dallas [2010–2015]
Faculty Associate
University of Texas at Dallas [2007–2018]
Center for Global Collective Action
Assistant Professor
University of Texas at Dallas [2005–2010]
Assistant Professor
University of North Texas [2001–2005]

Projects

Event Count Time Series Models
2018–2018 Brandt, Patrick T. ITV series with students from the Universities of Minnesota, Illinois, Wisconsin and Ohio State. University of Minnesota, Minneapolis, MN
Advances in Bayesian Time Series Modeling and The Study of Politics: Theory Testing, Forecasting, and Policy Analysis
2018–2018 Brandt, Patrick T. and John R. Freeman. Konstanz University, Konstanz, Germany
Modeling Macro Political Dynamics: The Pitfalls of Parsimony
2018–2018 Brandt, Patrick T. College of William and Mary
Multiple Time Series Models
2018–2018 Brandt, Patrick T. Two-day workshop on dynamic simultaneous equation, vector autoregression (VAR), and Bayesian VAR models. University of Texas, Dallas, Richardson, TX
It's a Dynamic Multivariate Uncertain World: Policy Evaluation in Political Science
2018–2018 Brandt, Patrick T. and John R. Freeman. New Methods Series. University Of Pittsburgh, Pittsburgh, PA

Presentations

Changepoint models: Statistics and Time Series for policy intervention and change identification
2022/11–2022/11
Sustaining Modern Infrastructure For Political And Social Event Data
2022/09–2022/09 Brandt, Patrick T., Khan, Latifur, D’Orazio, Vito, and Osorio, Javier 
CSSI-PI Meeting, Alexandria, VA 

Additional Information

Professional Memberships
  • American Political Science Association
  • Midwest Political Science Association
  • International Studies Association
  • Society for Political Methodology
Honors and other recognitions
  • Robert H. Durr Award, Midwest Political Science Association's prize for the best paper applying quantitative methods to a substantive problem at the 2006 meeting. Published as Sattler, Thomas, John R. Freeman and Patrick T. Brandt. 2008. Popular Sovereignty and the Room to Maneuver: A Search for a Causal Chain" Comparative Political Studies

Awards and Fellowships
  • Research Fellow, Workshop in Political Theory and Policy Analysis, Indiana University, Fall 1999. 
  • John V. Gillespie Memorial Scholarship, Department of Political Science, Indiana University, Summer 1999.
  • Political Science Departmental Fellowship, Indiana University, 1994-1996.
  • Governor's Fellow, Governor's Commission on Government Reform, Richmond, Virginia, Summer 1994.
  • W. Warner Moss Prize, Department of Government, College of William and Mary, 1994.

News Articles

Study: Paying Terrorist Kidnappers Doesn't Pay Off for Countries
Study: Paying Terrorist Kidnappers Doesn't Pay Off for Countries Paying ransoms to terrorist kidnappers may encourage more abductions and worsen the situation for others, according to new research from UT Dallas.

Countries that negotiated with terrorists to release hostages faced up to 87 percent more kidnappings than those that did not pay ransoms, according to the research, which was recently published in the European Journal of Political Economy.

“Every time you get one person back, and you did it by giving in, you’re going to have approximately another one taken. You’re essentially trading one for one,” said Dr. Todd Sandler, senior author of the study.

Funding

Frameworks: Infrastructure For Political And Social Event Data Using Machine Learning (with Patrick T. Brandt, Vito D’Orazio, Latifur R. Khan, Javier Osorio, Jared Edgerton)
$1,589,016 - National Science Foundation, CSSI-OAC-2311142 [2023/08–2026/07]
This project intends to revolutionize computerized data extraction for conflict scholars, security analysts, and practitioners who for decades have devoted significant resources to monitor, understand, and predict armed violence, social protests, and other politically relevant events worldwide. Currently, the vast majority of conflict event data are expensively coded by humans from increasingly large volumes of news reports. This project uses recent advances in artificial intelligence and large language models to address this fundamental issue for conflict research. It builds on earlier NSF efforts that created a publicly available large language model to study inter- and intra-state conflict and armed violence, called ConfliBERT. This project expands the ConfliBERT model to multilingual settings, including Arabic and Spanish. This will help researchers and policymakers better understand the context of local events and create a continuous data analysis process by feeding in current news stories to identify new political actors and events in real time. As the project's cyberinfrastructure develops, the research community will be empowered through training, education, and outreach with groups at local, national, and international levels, including academics and government.
Elements: Data: Sustaining Modern Infrastructure For Political And Social Events. (Patrick T. Brandt, Latifur R. Khan, Sultan Alsarra, Yibo Hu, Javier Osorio)
200000 ACCESS Credits - ACCESS / NSF [2022/11–2023/11]
GPU and HPC resource allocation.
Sustaining Modern Infrastructure For Political And Social Event Data
$588,032 - National Science Foundation CSSI-OAC-1931541 [2019/10–2023/09]
This project extracts quantitative summaries of political and international conflict events among national and non-state actors across the world by combing news reports across the internet in multiple languages. This generates event data, a machine-coded description of someone doing something to someone else as extracted from news reports. The project focuses on political and social events about conflict and cooperation between governments, individuals, non-governmental organizations, rebel groups, and others. The main goal of this project is to integrate and expand the end-to-end cyberinfrastructure for the robust creation, validation, access, and analysis of political event data by national security, government, academic, and non-governmental actors. A major component of this proposal is to continue to grow the project's engagement with the global event data community.
Big Data Driven Advanced Data Science Course Curriculum Development, Latifur Khan, Patrick T. Brandt, Nicolas Ruozzi, Bhavani Thurasingham
$230,789 - NSA [2018/09–2019/09]
Modernizing Political Event Data for Big Data Social Science Research, Patrick T. Brandt (PI, EPPS), Vito D’Orazio (Senior Personnel, EPPS), Jennifer S. Holmes (Co-PI, EPPS), Latifur R. Khan (Co-PI, ECS), Vincent Ng (Co-PI, ECS)
$1,497,358 - National Science Foundation RIDIR 1539302 [2015/09–2019/08]
The project creates a general research platform to study civil protests, international conflict, and civil unrest using texts from Spanish, Arabic, and French, in addition to English. This expands the development of programs, data and services available for coding regional conflict and cooperation methods beyond the current English-only approaches to enable data-rich research that will advance new approaches to core questions in the social, behavioral, and economic sciences. The project includes an openly available website that allows for the extraction and reporting of conflict events across the globe as well as the identification of their causes and diffusion. The project's data and methods help make data-driven decisions about foreign policy, civil war prevention, human rights policies, and the effects of other factors such as environmental or economic policies on these phenomena.