Computational Reading of Gender in Novels

1770–1922

The first project of the MIT Digital Humanities Lab analyzed the description of gender and gender roles across a large repertory of novels in the English language, primarily from the nineteenth century and early twentieth century. Our goal was to build computational tools that helped us understand how conceptions of gender were expressed and changed through distant reading of thousands of books. Our database involves over 4200 novels sourced from the Gutenberg project and gives us a comprehensive look at the views of authors of the time period.

Our Goals

As the first project of the lab, we are very excited to begin our research in the field of gender studies. The use of gender has changed over the centuries, not only in our culture, but also in its role in our literature. We are directing our research at novels written by authors as famous as Jane Austen and others that are much more obscure, such as Mary E. Mann. By looking at the history of our books, we hope to be able to study the ever-adapting and changing view on gender by writers all around the globe in the nineteenth and twentieth centuries.

It is the hope of the lab that by embarking on this mission, we are able to draw on the views and opinions of the past to diagnose potential causes, solutions, and sources of gender-based discrimination and stereotyping. We have asked questions and performed comparisons such as examining passive and active voice, pronoun frequencies, and much more.

Use the links above to explore what we’ve been doing!

This work is licensed under a Creative Commons Attribution 4.0 International License.