We are thrilled to announce that Arthur Spirling, the Interim Deputy Director at the Center for Data Science, has been awarded a $750,000 grant from the National Science Foundation for a project titled, “Computational and Historical Resources on Nations and Organizations for the Social Sciences (CHRONOS).” Spirling, along with colleagues and collaborators from Columbia University, will be developing tools to analyze millions of declassified U.S. government records, as a way of studying American foreign relations.
In the first stage of CHRONOS, Spirling and his collaborators will be using named-entity recognition processes—a type of natural language process that analyzes strings and combinations of words, as opposed to single words—to categorize how different foreign policy actors are being talked about within these declassified documents.
The second stage of CHRONOS will use topic modeling, a time-series application that will track how these mentions of foreign policy actors are changing over time.
Finally, Spirling and his colleagues will use social network extraction—a system of processes that extract social insights from text documents—to examine informal relationships between policy actors, as a way of determining how informal interactions are influencing foreign policy.
All of this research will eventually be available online, and data science practitioners will be able to use the tools that Spirling and his colleagues are employing, as a way of furthering, validating, and testing the CHRONOS project.
The most obvious implication of the project is an increased amount of information regarding declassified government documents, but Spirling wrote on the National Science Foundation’s website that the project’s findings could also improve the infrastructure that is available for multidisciplinary research and teaching.