Using big data analytics techniques, researchers at Dartmouth College have created a taxonomy of the world’s constitutions. This analysis is discussed in the EurekAlert! article “Big data creates family tree of constitutions.”  EurekAlert! is a service of the American Association for the Advancement of Science (AAAS).

The Dartmouth study applied subject indexing to the documents in order to define constitutional topics, and used machine learning to elucidate the flow of these topics over time and across documents. The analysis applied data visualization to the semantic connections between documents to reveal how constitutional concepts, and the constitutions themselves, evolved.

Researchers had theorized that the evolution of constitutional topics followed a process akin to biological evolution. The Dartmouth research used machine learning to organize constitutions by topics and identified the flow of topics over time between constitutions. The researchers demonstrated that evolution of constitutions followed the Yule Process, a mathematical model of a birth-death process.


Melody K. Smith

Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.