Depending on participant interest, this workshop will discuss either (1) principal component analysis or (2) word embeddings as a technique for exploring large digitized corpora, with particular emphasis on applications to literary and historical study. The workshop will be conducted using Jupyter notebooks in Python.

No prior experience with Python is assumed, but elementary knowledge of Python will be helpful. Participants will learn what these techniques are, some of the assumptions these techniques make, and how they can immediately apply these techniques to their own set of literary or historical texts. Larger implications of using these techniques for humanist study will also be discussed.

Skill Level
Beginner to Intermediate

Prerequisites
None

Equipment Requirements
Laptops required, participants will access jupyter notebooks via their web browser (no install required)