Computational Analysis of Literature
Jonathan Gordon (Computer Science)
This project will build on URSI research that created an electronic corpus of literature annotated with biographic, geographic, and publication metadata. Using modern natural language processing and data science methods, we will design tools to explore linguistic and thematic variation in the corpus across bounds of time, space, and society.
Required: Strong programming skills and an interest in natural language processing, linguistics, or digital humanities.
Preferred: Coursework in computer science (especially CMPU 203, 240, and 366), data science, cognitive science, linguistics, or literature, and experience programming in Python.
How should students express interest in this project?
In the application, state any relevant coursework, experiences, or skills. Students don’t need to contact me before submitting an application but are welcome to email questions.