This seminar will provide you with an overview of quantitative text analysis methods that allow you to systematically extract information from political texts. The seminar will combine more traditional approaches such as manual hand-coding with recent advances in political methodology that treat words as data. The seminar will begin with important concepts in content analysis such as content validity and intercoder reliability. We will afterwards take a closer look at manual coding approaches such as the Manifesto Project before turning to computer-assisted dictionary-based text analysis techniques. This will be followed by an extensive discussion of Wordscores and Wordfish, two cutting-edge techniques that allow you to automatically extract policy positions from political texts. Finally, we will deal with document classification and learn how to automatically classify texts into categories such as classifying thousands of press releases into policy areas. The seminar will combine theoretical sessions with practical exercises to allow participants to immediately apply the presented techniques.
Grimmer, Justin and Brendon Stewart (2013): Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts, Political Analysis, 21(3): 267-297.
Krippendorff, Klaus (2013): Content Analysis: An Introduction to Its Methodology, Thousand Oaks: Sage, Third Edition,
Neuendorf, Kimberly A. (2016): The Content Analysis Guidebook, Second Edition, Thousand Oaks: Sage.