Text As Data

Term: UMass - Spring 2026

Course Overview

With the recent explosion in availability of digitized text, social scientists increasingly are turning to computational tools for the analysis of text as data. In this three credit course, students will first learn how to convert text to formats suitable for analysis. From there, the course will introduce and proceed through tutorials on a variety of natural language processing approaches to the treatment of text as data. The goals of this course are (1) exposure to text as data research, (2) literacy to understand, evaluate, and critique text as data research, (3) skills to conduct basic and advanced text as data research, and (4) ability to communicate text as data research and articulate its real-world relevance.