code on a computer screen

We all know that computers do not have feelings. Yet how might we leverage technology to think about what it is to be human; to identify the emotional state of a speaker; to anticipate the affective response a text aims to produce in a reader or audience member? Or what kinds of questions can you ask about 100 novels that you can’t ask when reading a single book? What insights about human creativity arise from taking advantage of computer programs capable of working with very large data sets? These are just some of the questions that we will take up in Literature and Data Science, an experiment in new methods of literary inquiry.

This course provides an introduction to the use of computational methods in literary criticism. The class begins by exploring recent work in the field. We will consider the theoretical and methodological implications of using computers and statistical algorithms to analyze literature while also developing the necessary coding skills to enter into this conversation. The course will be largely hands-on, involving multiple projects designed to build the fundamental skills required for digital textual analysis.

Students will also be asked to evaluate and think critically about this kind of scholarship. We will work together to learn the basics of text mining and will undertake a range of projects, from tracking word frequency to performing sentiment analysis. Literature and Data Science aims to cross disciplinary boundaries, to nudge us all outside of our comfort zones, and to do work in a collaborative learning environment where we collectively value and cultivate innovation and creativity. People with coding experience are welcome, but no prior programming knowledge is required or expected. Laptops are required.

Taught by Rachael Deagman Simonetta.