The Math of Meaning—Counting and Modeling Textual Data

How do you compare a thousand documents at once? This session covers the core methods for turning text into structured data you can count, compare, and model: bag-of-words representations, term frequency–inverse document frequency (TF-IDF), and measures of similarity. We'll work through hands-on examples and look at how the size of a collection changes what analysis can reveal — along with what these methods necessarily leave out, and how they connect to modern language AI.