Introduction to Computational Text Analysis

This course provides an overview of sociological approaches to big data, with a specific focus on the analysis of large textual corpora. Covered topics include obtaining data from online sources through web scraping, APIs, and crowdsourcing; reserch ethics; data storage and pre-processing; and a range of analytical methods, including dictionary approaches, supervised machine learning, topic modeling, sentiment analysis, word embeddings, and network analysis. Students will learn how to program in Python, how to parse data in HTML, JSON, and XML formats, and how to properly document and distribute their work. While the course focuses on applied knowedlge of computational methods, it also address the affordances and limitations of text analysis as an anaytical approach to answering sociological research questions.