Introduction to
Computer-Assisted Text Analysis

Prof. Dr. Mirco Schoenfeld

Prof. Dr. Joel Glasman

28th April 2025

Each day, 328.77 quintillion Bytes
of new data are created on the Internet.

32877000000000000000000 Bytes

328.77 million Terabytes.

With less zeros:
Wikipedia

What are computers good at?

Are you doing text analysis with your PC already?

How should someone from your discipline use the PC for text analysis?

How do we get the PC
to analyze data for us?

We learn methods and evaluation techniques
for analyzing (large) text corpora.

By the end of the course,
you will know basic methods
for analyzing large document collections in R
and have a solid understanding of the results produced.

Organizational Matters

Your Projects

  • Find a relevant research question
  • Collect or download data that allows answering the question
  • Present your results on a poster
  • Outline technical details in a short technical report
  • You can team up with somebody else

Introduction to Methods

Prepare the topic of the sessions by
watching the videos and
doing it by yourself

https://mircoschoenfeld.de/seminar-introduction-to-computer-based-text-analysis-latest-iteration.html

https://mms.uni-bayreuth.de/Panopto/Pages/Sessions/List.aspx?folderID=2aa7b4b0-5890-4e85-aa88-ae7e0095afb5

Organizational bits

Access to slides, code & material

https://mircoschoenfeld.de/seminar-introduction-to-computer-based-text-analysis-latest-iteration.html

What are we doing in class then?

During class we will discuss
obstacles and problems.

Please bring your laptops.

Important Dates

Date What
16. June 2025 Discussion of Project Idea and Research Question
23. June 2025 Deadline for Blogpost and peer review in the session
7. July 2025 Preliminary Poster Presentation
16. July 2025 Poster Deadline (Subject to change – might be later) (FINAL)
21. July 2025 Poster Presentation
31. August 2025 Technical Report due (Discussable)(FINAL)

Blogpost

Deadline: 23.6.2025, Ca. 800 words

Contents:

  • Very short abstract
  • Motivation and context
  • Research question
  • Description of current state of research
  • Description of data acquisition
  • Outlook to further research questions

Meta:

  • Intermediate headlines
  • Pictures/figures with captions and sources
  • Quotes and citations
  • Reference section at the end
  • Your name

Can be published if it is good and you agree

Technical Report

Deadline: 31.8.2025, Max. 10 pages.

Keep it short

Avoid redundancy with the poster

Outline the technical(!) details of your project here

Submission of Blogpost and Poster

https://elearning.uni-bayreuth.de/course/view.php?id=37827

Staying in Touch

https://element.dmwg.uni-bayreuth.de

Data Literacy

This course is part of the supplementary course of studies!

https://www.dataliteracy.uni-bayreuth.de/

Back to Seminar