|
Instructors: Daniel Baumann
Event type:
Seminar / exercise
Org-unit: Politics, Administration & International Relations
Displayed in timetable as:
Advanced Methods | X
Hours per week:
1,5
Credits:
3,0
Location:
Campus der Zeppelin Universität
Language of instruction:
German
Min. | Max. participants:
5 | 30
Priority scheme: Standard-Priorisierung
Course content:
A central challenge of our time is analyzing an ever-growing volume of texts. Every day, new collections are created that no human being can analyze in a reasonable amount of time: be it newspaper articles, statements, minutes, blog posts or social media posts.
In order to facilitate the analysis of large amounts of text, we use computer-based methods. In this seminar, students will learn to apply such methods for quantitative text analysis, methods for extracting text-based information and statistical methods for analyzing large text corpora.
As Python is the most commonly used programming language for modern text analysis, the course will include a brief introduction to Python to ensure a basic understanding of the code used. Previous knowledge of Python is therefore not a requirement.
Students will also be introduced to working with AI chats such as ChatGPT and Google's Bard to facilitate the implementation of text analytics methods on this type of data.
As the main empirical example in this seminar, we will use the dataset of debates in the United Nations Security Council (Schönfeld et al. 2019). It includes all speeches in the UN Security Council from 1995 to 2020.
In addition, Prof. Dr. Steffen Eckhard offers a complementary seminar entitled: "Computational Text Analysis in Political Science: Applications", which focuses on use cases of text analysis methods in political science research fields.
Educational objective:
After successful completion of the seminar, students will be familiar with a range of methods and applications for working with text as data and computer-based text analysis and will be able to apply these methods in their own research projects.
Further information about the exams:
The students should apply one of the text analysis methods they have learned to a text data set of their choice in a first small project and explain their approach and the single steps they implement.
Mandatory literature:
- Baturo A., Dasandi N., Mikhaylov S. J. (2017): Understanding state preferences with text as data: Introducing the UN General Debate corpus, Research & Politics, 4(2), 1-9. https://doi.org/10.1177/2053168017712821
- Eckhard Steffen, Patz Ronny, Schönfeld Mirco, Meegdenburg Hilde van (2021): International bureaucrats in the UN Security Council debates: A speaker-topic network analysis, Journal of European Public Policy, https://doi.org/10.1080/13501763.2021.1998194
- Grimmer J., & Stewart B. (2013): Text as Data: The Promise and Pitfalls of Automatic Content Analysis Methods for Political Texts. Political Analysis, 21(3), 267-297. https://doi.org/10.1093/pan/mps028
- Grimmer J., Roberts M. & Brandon S. (2022): Text as Data – A New Framework for Machine Learning and the Social Sciences, Princeton University Press, ISBN: 978-0-691-207544.
- Schönfeld M., Eckhard, S., Patz, R., & van Meegdenburg, H. (2019). The UN Security Council Debates 1995-2017. Retrieved from: https://arxiv.org/abs/1906.10969
Wenn Sie E-Learning Funktionalitäten nutzen möchten, tragen Sie bitte "Ja" ein.:
ja
|
