Purdue Libraries and School of Information Studies News

SPRING ’21 Course Spotlight on ILS 69500:  Introduction to Computational Text Analysis in the Humanities and Social Sciences

October 30th, 2020

ILS 695:  Introduction to Computational Text Analysis in the Humanities and Social Sciences

Meeting Times: TR 3:00-4:15 (Online)

Instructor: Trevor Burrows

Computational analysis of textual data has become increasingly important in the world of digital humanities, digital history, data science, and computational social science. This course provides an introduction to the methods, debates, controversies, and tools of computational text analysis (CTA) specifically crafted for the humanities and social science graduate student. Students will explore the central theoretical debates in CTA while also learning practical hands-on skills in corpus creation, OCR, text mining, topic modeling, sentiment analysis, and other methods. They will learn how CTA relates to established interpretative practices in the larger histories of the humanities and social sciences and the broader context of their own disciplines, and will consider both the possibilities and the limitations of CTA in their own work. While the course is designed for a beginner with little technical training, students will become familiar with the basic elements of coding/ scripting using the programming language R and other tools. Upon completion of this course, students will understand the challenges of CTA, be conversant with major theoretical discussions around CTA, and have a foundational understanding of the steps required to incorporate CTA into their regular research practices and particular projects.

Learning Outcomes

1. A firm grasp of the basic steps required to perform CTA for both exploratory and analytic purposes, and an understanding of its potential applications and limitations

2. Understanding of critical debates around CTA, its use in humanities and social science research, and its use in the student’s own discipline

3. Understanding of CTA’s relationship to broader histories of language, interpretation, and both qualitative and quantitative research methods and epistemologies (i.e., philosophy of language, history of the book, critical theory)