PSC 534SEM - Text as Data

This course is an introduction to the use of digitized texts (such as parliamentary records, committee proceedings, laws, court opinions, international treaties, news reports, and social media) as sources of data for political scientists. You will learn to computationally retrieve, analyze, and model data by writing scripts using Python, R, and other current software. The course introduces students to the state of the art in the field of applying computational text analysis to the study of politics. It covers the most widely used methods for the empirical analysis of textual data, from the preprocessing stages to the interpretation of findings. By the end of the course, students will have gained expertise with an important branch of computational social science and developed skills with the Python programming language. Furthermore, students will have a deep contextual understanding of how these tools contribute to the production of political science research and will be able to deploy these tools to conduct their own such research. No previous experience with computer programming is necessary to enroll in this course.

Credits: 3

Term Typically Offered: Spring

Requisites: Pre-Requisites: PSC 508 (or one of the following COM 508, GEO 505, PSY 607, SOC 504 or permission of instructor)