Word Counting
Concordance
Reading / Viewing
Word Counting Basics
Creative Inspiration
Text Analysis
TF-IDF
Bayesian Text Classification
Reading
Part of the challenge of understanding algorithmic oppression is to understand that mathematical formulations to drive automated decisions are made by human beings. While we often think of terms such as βbig dataβ and βalgorithmsβ as being benign, neutral, or objective, they are anything but.
Assignment
Choose a text or data source and count word frequencies following the examples above. Design your own creative output. This need not be visual (sonify word counts?) nor does it require code (knit your own word frequency scarf!) Some things to consider:
- Use a language other than English!
- What happens if you compare different texts according to word frequency?
- Can you look at frequency of how words appear next to each other?
Reflect on your process of word counting and consider the following questions:
- Did you discover anything new about the text by counting words?
- What is lost from word counting?
- Challenge the assumption that algorithms for analyzing text (such as word counting) are neutral.
Add your assignment below via Pull Request
(Please note you are welcome to post under a pseudonym and/or password protect your published assignment. For NYU blogs, privacy options are covered in the NYU Wordpress Knowledge Base. Finally, if you prefer not to post your assignment at all here, you may email the submission.)
Emoji Key for Video Tutorials, Readings, and more
- π¨ Watch this video tutorial! (this is technical info needed for the examples). Of course if you alreaddy know this material, you can skip.
- π’ This is found in a group, maybe pick just one to check out!
- πΏ Additional video if you have a particular interest and want to do a deeper dive.
- π Required reading! Letβs make sure we all have read this.
- π Optional additional reading for a deeper dive.
- π» Code examples here!
- π Extra reference material / link