The behavioral modeling and computational social sciences initiative is an interdisciplinary group of researchers primarily within the Georgia Tech Research Institute and with research collaborations across Georgia Tech that perform strategic research and development in the field of computational social science and behavior modeling; focuses include the assessment of individual behavior, complex social interactions, and population-level events. By combining machine learning, graph theory, and simulation science with the social sciences, such as experimental psychology, sociology, and economics, we address fundamental national and international challenges in defense, economics, and security.
Erica Briscoe
GTRI Aerospace, Transportation and Advanced Systems Laboratory
Dr. Erica Briscoe is a Research Scientist at Georgia Tech Research Institute. Her research interests include the computational modeling of behavioral processes for individuals and groups, visual and machine perception, human concept formation and categorization, and the analysis of information processes within social media. At GTRI, she performs research related to the adversarial behavior of individuals and groups involved in asymmetric warfare, terrorist radicalization, technology adoption, and the use of social media.
Dr. Briscoe received a BS degree in Industrial Engineering from Georgia Tech, an MS degree in Information Systems from Drexel University, and an MS and PhD from Rutgers University in Cognitive Psychology.
Scott Appling
GTRI Aerospace, Transportation and Advanced Systems Laboratory
Scott Appling is Computational Social Scientist in ATAS and a member of the Behavioral Modeling and Computational Social Sciences Group at the Georgia Tech Research Institute. His broad research interests are in the fields of computational social science, data science, intelligent systems, and narrative intelligence. Some of his current work includes: the profiling of individuals and groups by combining social science theories, statistical natural language processing and applied machine learning; persuasive language generation for social influence bots. In the fields of disaster response/emergency management he has built information classification models that work in real-time to recognize specific kinds of disaster-related information using social computing and related data.
He holds Masters and Bachelors Degrees in Computer Science with a focus on Intelligent Systems and Natural Language Understanding from Georgia Tech's College of Computing.
Clayton 'CJ' Hutto
GTRI Electronic Systems Laboratory
C.J. Hutto is a Research Scientist working in the Human Systems Integration (HSI) Division at the Georgia Tech Research Institute (GTRI). He has a B.S. in Human Factors, a M.S. in Human Computer Interaction (HCI), and is currently pursuing a doctoral degree in Human Centered Computing (HCC) from the Georgia Institute of Technology. C.J.'s current fields of interest travel along two dimensions: The first is related to applications of Human Systems Integration (HSI) to analyze, design/develop, and test/evaluate the human-related systems engineering elements of systems undergoing DoD acquisition. Of special interest is modeling human performance in complex socio-technical systems (e.g., aircraft flight deck/cockpit, mission operations center, ship's bridge, etc.). The second dimension is related to developing agent-based models to simulate and predict human behavior within complex social systems (e.g., socio-cognitive networks), and analyzing human social, cognitive, and cultural behavior.
Jason Poovey
GTRI Information and Communications Laboratory
Mr. Jason Poovey has an MS in Computer Engineering from North Carolina State University and is the Branch Head of the HPC, Data Analytics, and Software Engineering Branch at the Georgia Tech Research Institute. He has worked at GTRI since 2012, with previous experience on the reporting team at AthenaHealth, and experience as a Graduate Research Assistant working in the field of Computer Architecture at Georgia Tech since 2009. Jason is also an experienced instructor having taught introductory computer engineering and architecture at North Carolina State University, introductory computer science at Emory University, and Advanced Parallel and Distributed Architecture at Georgia Tech.
At GTRI Jason’s work has focused on creating high performance solutions to a wide variety of problems and applying analytics to large quantities of data. This research has spanned the field from social media analysis, business intelligence, systems engineering, health analytics, Internet of Things research, and network analysis. Jason is active in the research community with numerous refereed technical papers and active membership in the IEEE Computer Society.
David Ediger
GTRI Information and Communications Laboratory
Dr. David Ediger’s current work centers on developing new and emerging high performance computing capabilities with a focus on smart cities and streaming data fusion. He has conducted high level research and co-authored many publications in graph algorithms and social network analysis using large-scale high performance computing platforms and novel hardware. He is a lead developer of GraphCT and STINGER, open source packages for large graph analysis.
Dr. Ediger received his Ph.D. and M.S. in Electrical & Computer Engineering from Georgia Tech. He completed his B.S. in Computer Engineering under the direction of Dr. Tarek El-Ghazawi at The George Washington University.
Online Social Science Experimentation
Credibility & Deception in Online Social Networks
- Briscoe, Erica J., Darren Scott Appling, and Heather Hayes. "Social Network Derived Credibility." Recommendation and Search in Social Networks. Springer International Publishing, 2015. 59-75.
Data Science
Utilization of large data for complex statistical analyses, including NLP.
- Ediger, D., Appling, S., Briscoe, E., McColl, R., & Poovey, J. (2014). Real-Time Streaming Intelligence: Integrating Graph and NLP Analytics. 2014 IEEE High Performance Extreme Computing Conference.
Tailored Tool Development
Disaster & Disease discovery and open source monitoring.
- S. Appling, E. Briscoe, A. Carpenter, L. McCook, G. Scott, T. Allen, R. Buettner, C. Oros. (2015). Social Media for Situational Awareness: Joint-Interagency Field Experimentation (2015). Humanitarian Technology. Boston, MA.
Social Media Analytics
Analysis of social media data.
- Hutto, C. J., Gilbert, E., & Yardi, S. (2013). A Longitudinal Study of Follow Predictors on Twitter. 2013 ACM annual conference on Human Factors in Computing Systems (CHI). Paris, France.
Predicting Emerging and Disruptive Technology
Utilizing open-source data to understand and visualize the global technology landscape and create business intelligence.
- Briscoe, E. J., Appling, S., & Schlosser, J. (2015). Passive Crowd Sourcing for Technology Prediction. In Social Computing, Behavioral-Cultural Modeling, and Prediction (pp. 264-269)
Multi-scale Modeling and Analysis of Terrorism and Radiclization
Characterizing influences through integrating multi-scale behavioral models.
- Weiss, L., Briscoe, E., Wright, W. Kline, K., Horgan, J., Cushenbery, L. & Hilland, C. (2013). A Model Docking System for Understanding Radicalization. Proceedings of the IEEE Intelligence and Security Informatics Conference.
Socio-Economic Modeling
Experimental economics and marketing research to inform pricing strategies utilizing social networks and graph theory.
- Galloway, E., Mappus, C., & Briscoe, E. (2013). Social Price Targeting: Use of Network Structure in Firm Decision Making. 9th Conference of the European Social Simulation Association Warsaw School of Economics
User Profiling and Insider Threat Detection
Profiling and identifying anomalous users with computer behavioral trace modeling.
- Mappus, C. & Briscoe, E. (2013). Layered behavioral trace modeling for threat detection. Proceedings of the 2013 IEEE Intelligence and Security Informatics Conference.
Socio-Cognitive Modeling
Experimental work and modeling of belief formation and propagation.
- Mappus, R., Briscoe, E., & Hutto, C. (2012). Optimized Influence Targeting for Adoption in Social Networks. Proceedings of the 3rd Annual Conference of the Computational Social Science Society of America.