I look at the beach and then at the table surrounded by nerds, deep in thought and conversation about Dirichlet priors, matching algorithms, and armed conflicts. This peculiar (in the best way) environment catalyzes a moment of reflection: how did I get here?
Four years ago, as a second-year statistics PhD student, I watched "Guatemala: The Secret Files" on PBS Frontline World. I listened to stories of family members who disappeared without answers or justice. Then the story shifted to the work being done by archivists and data experts at Guatemala's Historic Archive of the National Police. The scientists' pursuit of the truth energized me. I ...
New paper in Biometrika, co-authored by HRDAG's Kristian Lum and James Johndrow: Theoretical limits of microclustering in record linkage.
Amelia Hoover Green. In Collective Violence and International Criminal Justice: An Interdisciplinary Approach, ed. Alette Smeulers, Antwerp, Belgium. © 2010 Intersentia. All rights reserved. [Link coming soon]
On Wednesday, February 4, in Pristina, international experts praised the Humanitarian Law Centre’s database on victims of the Kosovo conflict, the Kosovo Memory Book. HRDAG executive director Patrick Ball is quoted in the article that appeared in Balkan Transitional Justice.
Doing an investigation on the contents of the Archive brought with it three major lessons. The first big lesson was the constant movement (nothing was static), The second great lesson was that everything evolved (the changes were a constant). The third major lesson was to discover how two institutions can work together while geographically far apart.
The constant movement
As there were other processes being carried out at the Archive, everything was in constant movement. In other words, one day the documents were in X location and tomorrow they may be in location Y or dispersed in multiple locations. This made it impossible to know with certai...
Violence against women in all its forms is a human rights violation. Most of our HRDAG colleagues are women, and for us, unfortunately, recent campaigns such as #metoo are unsurprising.
The Human Rights Data Analysis Group is composed of a diverse group of board members, full-time staff, and consultants. Employing a multidisciplinary approach, we work with experts in the fields of computer science, software development, mathematical and applied statistics, and demography.
Advisory Board
As a nonprofit organization, our Advisory Board serves as our governing body. This board helps us to make decisions, keeps us on track with our mission and goals, and oversees the organization in legal and logistical matters.
David Banks, Professor, Statistical Science, Duke University
Kim Keller, Executive Director, The Keller Foundation
Dinah ...
In our work, we merge many databases to figure out how many people have been killed in violent conflict. Merging is a lot harder than you might think.
Many of the database records refer to the same people--the records are duplicated. We want to identify and link all the records that refer to the same victims so that each victim is counted only once, and so that we can use the structure of overlapping records to do multiple systems estimation.
Merging records that refer to the same person is called entity resolution, database deduplication, or record linkage. For definitive overviews of the field, see Scheuren, Herzog, and Winkler, Data Quality ...
A follow-up chapter exploring recent advancements in LLM technology and extraction strategies.
Patrick Ball es un sabueso de la verdad. Ese deseo de descubrir lo que otros quieren ocultar lo ha llevado a desarrollar fórmulas matemáticas para detectar desaparecidos.
Su trabajo consiste en aplicar mĂ©todos de mediciĂłn cientĂfica para comprobar violaciones masivas de derechos humanos.
For more than 10 years, and with regularity, Mexican authorities have been discovering mass graves, known as fosas clandestinas, in which hundreds of bodies and piles of bones have been found. The casualties are attributed broadly to the country’s “drug war,” although the motivations and perpetrators behind the mass murders are often unknown.
Recently, HRDAG collaborated with two partners in Mexico—Data CĂvica and Programa de Derechos Humanos of the Universidad Iberoamericana—to model the probability of identifying a hidden grave in each county (municipio). The model uses an set of independent variables and data about graves from 2013 ...
Suddeutsche Zeitung writer Hakan Tanriverdi interviews HRDAG affiliate Anita Gohdes and writes about her work on the Syrian casualty enumeration project for the UN Office of the High Commissioner for Human Rights. This article, "BĂĽrgerkrieg in Syrien: Das Internet als Kriegswaffe," is in German.
Suddeutsche Zeitung
Hakan Tanriverdi
January 4, 2015
Link to story on SZ
Related blogpost (Updated Casualty Count for Syria)
Back to Press Room
Today The Tor Project announced that it has elected a new Board of Directors, and among them is HRDAG executive director Megan Price. The Tor Project is a nonprofit advocacy group that promotes online privacy and provides software that helps users opt out of online tracking.
Megan and Patrick have long maintained that encryption and privacy are essential for enabling human rights work. Patrick's ideas are described in Monday's FedScoop story about encryption, human rights, and the U.S. State Department.
“Human rights groups depend on strong cryptography in order to hold governments accountable," says Patrick. "HRDAG depends on local human ...
HRDAG is helping the Invisible Institute turn their windfall of raw data about police misconduct into data that can be analyzed.
Tarak Shah, Cristian Allen, Ayyub Ibrahim, Harlan Kefalas, and Bavo Stevens (2024). The Use of Unstructured Data to Study Police Use of Force. 5 December, 2024. CHANCE, 37(4), 18–23. https://doi.org/10.1080/09332480.2024.2434437
Tarak Shah, Cristian Allen, Ayyub Ibrahim, Harlan Kefalas, and Bavo Stevens (2024). The Use of Unstructured Data to Study Police Use of Force. 5 December, 2024. CHANCE, 37(4), 18–23. https://doi.org/10.1080/09332480.2024.2434437
