Computational & Digital Humanities Through Data+

Summer Undergraduate Research in the Humanities:

Data+ is a ten week summer research program based within the Rhodes information initiative at Duke. Undergraduate and masters students (from Duke and other universities) work in small (two or three students) teams, under the direction of a faculty member and a graduate student, and collaborate with other teams in a communal environment. They learn data analysis and visualization techniques, how research projects are designed and implemented, and how to work in a professional setting.

The humanities-based projects within Data+ couple big data analysis with the interpretive work usually done by humanists. By including humanistic projects in a program that had previously focused on STEM research, we introduce our undergraduates to a broader understanding of what it means to do research in both the humanities and in data science.

The data sets for these projects include collections of texts, images, videos, and audio—in other words, they are digital archives broadly understood. I train our students on how to select and “quantify” elements from text, video, audio, and still images in order to prepare them for statistical analysis. In our projects, we focus on how media creates and communicates meaning and how the students-as-researchers generate new meanings through data cleaning, analysis, and visualization.

Responsible research in these projects includes both practices (often) familiar to our students—such as documentation, citation, or code annotation—as well as reflections on accountability in analysis and presentation of results.