This course was offered in the Spring 2021 at the University of Copenhagen’s Department of Sociology. The background readings for the course come from Gabriel Ignatow and Rada Mihalcea’s Text Mining: A Guidebook for the Social Sciences while much of the applied readings come from Julia Silge and David Robinson’s Text Mining with R and Emil Hvitfeldt and Julia Silge’s Supervised Machine Learning for Text Analysis in R. You can find the course syllabus here and further course information on the university’s course listing site.
Course Description
Our contemporary, increasingly digital societies generate vast amounts of textual data that provide a rich source for sociological research. The scale of these novel data however poses a challenge to the approaches sociologists traditionally use to study texts. In response, automated methods of text analysis are becoming increasingly popular and the command of these methods a valuable skill in academic environments as well as on the private industry job market.
This course introduces students to quantitative text analysis, reviews selected methods falling within this category of approaches, and illustrates their implementation in the statistical programming language R. Students will learn about the origins of quantitative approaches to studying text and how they complement traditional, qualitative methodologies. Using recent peer-reviewed publications students will gain an understanding of how these methodological approaches can be used to answer sociological questions and, in hands-on lab sessions, students will learn to implement selected techniques in R.
After successful participation, students will be comfortable reading current sociological research using quantitative text analysis, have an understanding of the landscape of tools used within the literature, and will have gained experience with their implementation in R.