Michael P. Colaresi
University of Pittsburgh
IMG_3808.png

ReDSCAIP Lab

The Responsible Data Science, Complexity, and AI for Peace Lab (ReDSCAIP)

I run a research group that aims to extract social science inferences from text and other unstructured data here at the University of Pittsburgh. A hallmark of the lab is collaboration between all the members. Our current projects cover areas including human rights, horizontal inequalities, forecasting of conflict, and the intersection of digital technology, artificial intelligence, and democracy. We innovate computational resources that leverage machine learning/AI, knowledge graphs, natural language processing, Bayesian statistics, optimal transport, agent-based modeling, and network science to make progress on core social science questions. Former members have gone on to exciting opportunities in academia, government, and industry.

Members

Current

Merve Keskin | PhD Student, University of Pittsburgh

Laura Beghini Chelidonopoulos | PhD Student, University of Pittsburgh

Zhejun Qiu | PhD Student, University of Pittsburgh

Qing Chang | Post-Doc, School of Computing and Information, University of Pittsburgh

Minsu Jang | Post-Doc, Statistics and Quantitative Methods, University of Milano-Bicocca

Past (with ReDSCAIP and Text(Col)Lab)

Bree Bang-Jensen | Former Post-Doc

Daniel Gustafson (starting May 2020!) | Former Post-Doc

Kevin Greene | Former PhD Student

Yingfan Zhou | Former PhD Student

Haonan Duan | Former Masters Student

Nikunj Goel | Former Masters Student

Sai Pradeep Peri | Former Masters Student

Anna Baskin | Former Undergraduate Researcher

Baekkwan Park | Former Post-Doc

Matthew Jackson | Former PhD Student

Sidhi Srinivasachar | Former Undergraduate Researcher

Stephen Kandrak | Former Undergraduate Researcher

Bria Pullin | Former Undergraduate Researcher

Mitchell Luckman | Former Undergraduate Researcher

Azad Niroomand | Former Undergraduate Researcher

Annisa Chaudari | Former Undergraduate Researcher

Zuhaib Mahmood | Former PhD Student

Lora DiBlasi | Former PhD Student

Events

Featured
TextLab Members Win JPR's Best Visualization Award 2017
TextLab Members Win JPR's Best Visualization Award 2017

The Journal of Peace Research awarded Michael Colaresi and Zuhaib Mahmood the fifth JPR Best Visualization Award for their article Do the Robot: Lessons from Machine Learning to Improve Conflict Forecasting, published in the May 2017 special issue of the Journal of Peace Research.

From the JPR: “The jury was particularly impressed by the introduction of a new visual tool to assess the predictive accuracy of quantitative models. These ‘model criticism plots’ are part of an iterative cycle of model construction, evaluation and improvement, and help users identify observations where the difference between predicted and observed outcomes is particularly pronounced. In doing so, Colaresi and Mahmood’s graphs take the idea of separation plots (Greenhill, Ward & Sacks, 2011) one step further, and add an additional dimension to jointly evaluate absolute values, but also their rank in the overall sample.”


Projects

Understanding Adversarial Influence Campaigns in the Age of Digital Surveillance and Generative AI with a Multiplex, Agent-Based Model | Modeling the influence of adTech surveillance and GenAI through social media on Democracy

Populist PULSAR | Measuring the populist narratives with network motifs

Using Knowledge Graphs to Organize Spatial and Social Information on Horizontal Inequalities | Organizing the concepts on armed actors, locations, and social groups into a wikidata-linked KG

High resolution conflict forecasting | creating a policy-relevant early warning system

Summary Block
This is example content. Double-click here and select a page to feature its content. Learn more
Featured