Digital Humanities - Text as Data In-Person
The course offers an opportunity to gain an understanding of concepts such as language technology, "text mining" and "distant reading". In this course, we will start with user-friendly programs and websites. We will look at advanced use of Google Ngram Viewer to understand distant reading and big data. We will use Orange to collect texts from The Guardian and Wikipedia, and we will discuss some common algorithms for text mining on large datasets. With a basis in Voyant and Spyral, we will delve into algorithms and graphs to go in depth with smaller text collections.
Gain knowledge in:
- Distant reading with Google Ngram
- Data collection and analysis with Orange
- Graphs - lots of graphs in Voyant Tools and Spyral
The course lasts 2.5 hours with two short breaks and alternates between brief lectures followed by small exercises. The course takes place at KUB Southern Campus in the data lab on the second floor.
The course will be in English if there are participants who do not speak Danish.
Related LibGuide: KUB Datalab by Christian Knudsen
- Date:
- 09/04/2025
- Time:
- 9:30 - 12:00
- Time Zone:
- Central European Time (change)
- Location:
- KUB Datalab - Sdr Campus
- Campus:
- KUB Søndre Campus, Karen Blixens Plads 7, 2300 Kbh. S
- Audience:
- Level 1 - Beginner / Begynder
- Categories:
- Analysis Cleaning English Harvesting Visualisation Datalab
