Current Multidisciplinary Projects
TwoRavens: Automated Machine Learning and Data Exploration
TwoRavens is is a Web application for statistical modeling. Given a dataset, it automatically identifies interesting relationships and builds models to predict outcomes. Researchers impart substantive knowledge to define new problems and build better models to help solve their research question.
Modernizing Political Event Data
Modernizing Political Event Data is a project to collect and provide access to political event data coded from global news sources. TwoRavens for Event Data is an extension of the broader TwoRavens project to access and analyze this and other event datasets.
Crowdsourcing Militarized Interstate Dispute Data
Updating the Militarized Dispute Data Through Crowdsourcing is a project to develop and leverage crowdsourcing and natural language processing methods to construct a human(s)-in-the-loop system for collecting quality conflict data fast and efficiently.
TwoRavens is is a Web application for statistical modeling. Given a dataset, it automatically identifies interesting relationships and builds models to predict outcomes. Researchers impart substantive knowledge to define new problems and build better models to help solve their research question.
Modernizing Political Event Data
Modernizing Political Event Data is a project to collect and provide access to political event data coded from global news sources. TwoRavens for Event Data is an extension of the broader TwoRavens project to access and analyze this and other event datasets.
Crowdsourcing Militarized Interstate Dispute Data
Updating the Militarized Dispute Data Through Crowdsourcing is a project to develop and leverage crowdsourcing and natural language processing methods to construct a human(s)-in-the-loop system for collecting quality conflict data fast and efficiently.
Peer-Reviewed Journal Publications
2020 (forthcoming). "The Militarized Interstate Dispute Dataset: Putting Things in Perspective" (with Glenn Palmer, Michael Kenwick, and Roseanne McManus). International Studies Quarterly.
2019 (forthcoming). “Buying Blue Helmets: Foreign Aid and the Construction of UN Peace- keeping Missions” (with Andrew Boutton). Journal of Peace Research.
2019 (forthcoming). “Updating the Militarized Interstate Dispute Data: A Response to Gibler, Miller, and Little” (with Glenn Palmer, Michael Kenwick, and Roseanne McManus). International Studies Quarterly.
2019. “UTDEventData: An R package to access political event data” (with HyoungAh Kim, Patrick Brandt, Jared Looper, Sayeed Salam, Latifur Khan, and Michael Shoemate). Journal of Open Source Software 4(36): 1322. https://doi.org/10.21105/joss.01322
2018. “Who is a Terrorist? Ethnicity, Group Affiliation, and Understandings of Political Violence” (with Idean Salehyan). International Interactions 44(6): 1017-1039.
2016. "Crowdsourcing the Measurement of Interstate Conflict" (with Michael Kenwick, Matthew Lane, Glenn Palmer, and David Reitter). PLOS ONE 11(6): e0156527. doi:10.1371/journal.pone.0156527
2015. "Kickoff to Conflict: A Sequence Analysis of Intra-State Conflict Preceding Event Structures" (with James Yonamine). PLOS ONE 10(5): e0122472. doi:10.1371/journal.pone.0122472.
2015. "The MID4 Data Set, 2002-2010: Procedures, Coding Rules, and Description" (with Glenn Palmer, Michael Kenwick, and Matthew Lane). Conflict Management and Peace Science 32(2): 222-242.
2014. "Separating the Wheat from the Chaff: Applications of Automated Document Classification Using Support Vector Machines" (with Steven Landis, Glenn Palmer, and Philip Schrodt). Political Analysis 22(2): 224-242. PDF.
2012. "War Games: North Korea's Reaction to US and South Korean Military Exercises." Journal of East Asian Studies 12(2): 275-294. PDF. Replication.
2019 (forthcoming). “Buying Blue Helmets: Foreign Aid and the Construction of UN Peace- keeping Missions” (with Andrew Boutton). Journal of Peace Research.
2019 (forthcoming). “Updating the Militarized Interstate Dispute Data: A Response to Gibler, Miller, and Little” (with Glenn Palmer, Michael Kenwick, and Roseanne McManus). International Studies Quarterly.
2019. “UTDEventData: An R package to access political event data” (with HyoungAh Kim, Patrick Brandt, Jared Looper, Sayeed Salam, Latifur Khan, and Michael Shoemate). Journal of Open Source Software 4(36): 1322. https://doi.org/10.21105/joss.01322
2018. “Who is a Terrorist? Ethnicity, Group Affiliation, and Understandings of Political Violence” (with Idean Salehyan). International Interactions 44(6): 1017-1039.
2016. "Crowdsourcing the Measurement of Interstate Conflict" (with Michael Kenwick, Matthew Lane, Glenn Palmer, and David Reitter). PLOS ONE 11(6): e0156527. doi:10.1371/journal.pone.0156527
2015. "Kickoff to Conflict: A Sequence Analysis of Intra-State Conflict Preceding Event Structures" (with James Yonamine). PLOS ONE 10(5): e0122472. doi:10.1371/journal.pone.0122472.
2015. "The MID4 Data Set, 2002-2010: Procedures, Coding Rules, and Description" (with Glenn Palmer, Michael Kenwick, and Matthew Lane). Conflict Management and Peace Science 32(2): 222-242.
2014. "Separating the Wheat from the Chaff: Applications of Automated Document Classification Using Support Vector Machines" (with Steven Landis, Glenn Palmer, and Philip Schrodt). Political Analysis 22(2): 224-242. PDF.
- Reprinted in Advances in Political Methodology by Robert Franzese Jr. (ed). Northampton, MA: Edward Elgar Publishing
- Included in Political Analysis Virtual Issue 10, "Recent Innovations in Text Analysis for Social Science"
2012. "War Games: North Korea's Reaction to US and South Korean Military Exercises." Journal of East Asian Studies 12(2): 275-294. PDF. Replication.
- This research is featured in a blog by Stephan Haggard at the Peterson Institute. Check it out here.
Peer-Reviewed Conference Publications
2019. "Modeling and Forecasting Armed Conflict: AutoML with Human-Guided Machine Learning" (with James Honaker, Raman Prasad, and Michael Shoemate). 2019 IEEE Big Data: 3rd International Workshop on Big Data Analytics for Cyber Intelligence and Defense (BDA4CID), Los Angeles, CA, pp. 4714-4723.
2019. “Towards Human-Guided Machine Learning” (with Yolanda Gil, James Honaker, Shikhar Gupta, Yibo Ma, Daniel Garijo, Qifan Yang, and Neda Jahanshad). 2019 ACM Intelligent User Interfaces (IUI), Los Angeles, CA, pp. 614-624.
2018. “TwoRavens for Event Data” (with Marcus Deng and Michael J. Shoemate). 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, pp. 394-401.
2017. "RePAIR: Recommend Political Actors in Real-time From News Websites" (with Mohuiddin Solaimani, Sayeed Salam, Latifur Khan, and Patrick Brandt). Forthcoming in IEEE Big Data.
2017. "Automatic Political Actor Recommendation in Real-Time" (with Mohuiddin Solaimani, Sayeed Salam, Latifur Khan, and Patrick Brandt). In: Lee D., Lin YR., Osgood N., Thomson R. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2017. Lecture Notes in Computer Science, vol 10354. Springer, Cham.
2015. "Error-Correction and Aggregation in Crowd-Sourcing of Geopolitical Incident Information" (with Alexander Ororbia, Yang Xu, and David Reitter) In: Agarwal N., Xu K., Osgood N. (eds) Social Computing, Behavioral-Cultural Modeling, and Prediction. SBP 2015. Lecture Notes in Computer Science, vol 9021. Springer, Cham.
2014. "Statistical Modeling by Gesture: A Graphical, Browser-based Statistical Interface for Data Repositories" (with James Honaker). Extended Proceedings of ACM Hypertext 2014.
2019. “Towards Human-Guided Machine Learning” (with Yolanda Gil, James Honaker, Shikhar Gupta, Yibo Ma, Daniel Garijo, Qifan Yang, and Neda Jahanshad). 2019 ACM Intelligent User Interfaces (IUI), Los Angeles, CA, pp. 614-624.
2018. “TwoRavens for Event Data” (with Marcus Deng and Michael J. Shoemate). 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, pp. 394-401.
2017. "RePAIR: Recommend Political Actors in Real-time From News Websites" (with Mohuiddin Solaimani, Sayeed Salam, Latifur Khan, and Patrick Brandt). Forthcoming in IEEE Big Data.
2017. "Automatic Political Actor Recommendation in Real-Time" (with Mohuiddin Solaimani, Sayeed Salam, Latifur Khan, and Patrick Brandt). In: Lee D., Lin YR., Osgood N., Thomson R. (eds) Social, Cultural, and Behavioral Modeling. SBP-BRiMS 2017. Lecture Notes in Computer Science, vol 10354. Springer, Cham.
2015. "Error-Correction and Aggregation in Crowd-Sourcing of Geopolitical Incident Information" (with Alexander Ororbia, Yang Xu, and David Reitter) In: Agarwal N., Xu K., Osgood N. (eds) Social Computing, Behavioral-Cultural Modeling, and Prediction. SBP 2015. Lecture Notes in Computer Science, vol 9021. Springer, Cham.
2014. "Statistical Modeling by Gesture: A Graphical, Browser-based Statistical Interface for Data Repositories" (with James Honaker). Extended Proceedings of ACM Hypertext 2014.
External Funding for Original Investigations
2020 - 2022 |
Sustaining Modern Infrastructure for Political and Social Event Data National Science Foundation # OAC-1931541 ($588,032) Role: Co-PI Collaborators: Patrick Brandt, Jennifer Holmes, Latifur Khan, Javier Osorio |
2017 - 2021 |
TwoRavens: Intuitive Statistical Exploration, Model Extraction, and Curation DARPA Data-Driven Discovery of Models # FA8750-17-2-0114 ($1,700,000) Role: Co-PI ($348,166 to UTD) Collaborators: James Honaker |
2019 - 2020 |
Spark-based Political Event Coding National Science Foundation # SES-170012 Renewal XSEDE resource allocation estimated by NSF at $125,516 Role: Co-PI Collaborators: Patrick Brandt, Latifur Khan |
2015 - 2018 |
Updating the Militarized Dispute Data Through Crowdsourcing: MID5 National Science Foundation # SBE-SES-1528624 ($1,057,785) Role: Principal Investigator ($367,432 to UTD) Collaborators: Glenn Palmer, David Reitter |
2015 - 2018 |
Modernizing Political Event Data for Big Data Social Science Research National Science Foundation # SBE-SMA-1539302 ($1,497,358) Role: Senior Personnel Collaborators: Patrick Brandt, Jennifer Holmes, Latifur Khan, Vincent Ng 2017 - 2018 Spark-based Political Event Coding |
2017 - 2018 |
Spark-based Political Event Coding National Science Foundation # TG-SES-170012 (630,720 SUs) XSEDE resource allocation estimated by NSF at $105,267 Role: Co-PI Collaborators: Patrick Brandt, Latifur Khan |
Articles Submitted for Publication
"Conflict Forecasting and Prediction"
"Multinational Corporations and Political Violence: Trends and Forecasts" (with Alero Akporiaye and Clint Peinhardt).
"Multinational Corporations and Political Violence: Trends and Forecasts" (with Alero Akporiaye and Clint Peinhardt).
Working Papers
"A Human-Guided Machine Learning Algorithm for Conflict Forecasting."
"An Experimental Analysis of Crowdsourcing Designs for Conflict Event Data" (with Michael Kenwick, Matthew Kelly, Glenn Palmer, David Reitter, Zhanna Terechshenko, and Danielle Zaychik).
"Constraining Cooperation: Military Integration and Government Repression." PDF.
"Advancing Measurement of Foreign Policy Similarity." PDF.
"An Experimental Analysis of Crowdsourcing Designs for Conflict Event Data" (with Michael Kenwick, Matthew Kelly, Glenn Palmer, David Reitter, Zhanna Terechshenko, and Danielle Zaychik).
"Constraining Cooperation: Military Integration and Government Repression." PDF.
"Advancing Measurement of Foreign Policy Similarity." PDF.