Analytic Portals

To support social science researchers interested in using social media, newspapers, and other forms of text data, this data portal enables social scientists to generate structured variables using state of the art natural language processing, data mining, and machine learning. Our goal is to provide an easy to use infrastructure for social scientists to construct variables from organic data and blend them with other traditional variables. We also have projects that focus on creating new data sets to share with the public, including education data and survey data. Our infrastructure supports sharing and combining these other types of more traditional, structured data.


The available portals cover the 2020 presidential election, parenting, COVID-19, gun violence, and forced migration.


Training Date Sets

MDI makes multiple labeled data sets publicly accessible in order to provide training data for machine learning algorithms.