Applied Text Analysis from Close Reading to Machine Learning
Academic Program:
- Master of Arts in Comparative History (2 years) -- Track: Comparative History from 1500 till present time
- Master of Science in Mathematics and its Applications (1 year)
- Master of Arts in International Relations (2 years)
- Doctor of Philosophy in Network Science
- Master of Arts in Cultural Heritage Studies -- Track: Academic Research and Protection of Cultural Heritage
- Master of Science in Finance
- Master of Science in Mathematics and its Applications (2 years)
- Master of Arts in Sociology and Social Anthropology, with an optional specialization in Global and Urban Studies
- Master of Arts in Sociology and Social Anthropology
- Master of Arts in Political Science (2 years)
- Master of Arts in Political Science (1 year)
- Master of Arts in Late Antique, Medieval and Early Modern Studies
- Master of Arts in International Relations (1 year)
- Master of Arts in Women's and Gender Studies (GEMMA)
- Master of Arts in Gender Studies
- Master of Arts in European Women's and Gender History (MATILDA)
- Master of Arts in Critical Gender Studies
- Master of Arts in Comparative History (2 years) -- Track: Late Antique, Medieval, and Renaissance Studies
- Master of Arts in Comparative History (1 year)
- Doctor of Philosophy in Cognitive Science
Instructor: Jessie Labov, Levente Littvay, Marsha Siefert
Credits: 2.0
Course description:
This course will focus on the task of turning raw materials – both analog and digital – into a usable dataset for text analysis. It is meant as a supplement to the introductory course in text analysis (see UWC 5008), adding a practical and more skill-based environment. For each of the subjects treated in the introductory course, we will work through different hands-on approaches, introduce relevant software, and experiment with how to work with texts on a medium- to large-scale.
Prerequisite: Students in UWC 5009 must also be enrolled in UWC 5008. A basic familiarity with programming languages such as R or Python is strongly recommended, although advanced skills are not required.
Learning outcomes:
• create and clean a full-text corpus relevant to their research area
• extract relevant metadata from their corpus
• use basic tools for textual analysis (Voyant, Juxta, TaPOR, Mallet)
• grasp and describe the role of programming languages in more advanced “under the hood” techniques
• design research questions appropriate to textual analysis in their respective disciplines