Text as Data

Pre-req: SIPA IA6500 - Quant I, and prior experience with R are required. This course introduces students to the quantitative analysis of text, an increasingly important method in the social sciences and public policy. With vast amounts of textual information now available from sources such as social media, news articles, political speeches, and government documents, the ability to analyze text systematically is essential. Students will learn how to collect, process, and analyze text data to answer meaningful research questions.

The course covers a range of methods including dictionary-based approaches, supervised classification, topic modeling, word embeddings, and emerging applications of Large Language Models. Emphasis is placed on practical application through hands-on exercises using the R programming language. By the end of the semester, students will develop an original research project using text as data.