Understanding how data and text mining can help you make historical arguments.
- Read: Ted Underwood, “Seven Ways Humanists are Using Computers to Understand Text”
- Read: Dan Cohen, “From Babel to Knowledge: Data Mining Large Digital Collections”
- Explore: Cameron Blevins, “Topic Modeling Martha Ballard’s Diary”
- Come to class prepared to discuss the source material for your projects. What digital sources are you using?
Due Sunday, November 22nd at noon. Worth 3 points. Blog responses should be at least 300 words; they should be written in a semi-formal scholarly style (with complete thoughts and correct spelling, grammar, and syntax). Partial responses (including responses that fail to meet the minimum word length or clearly fail to answer the prompt) will receive partial credit. Late posts will not be accepted.
- Explore a topic of your choosing at one of the following sites–similar to the exercise we did in class: Time Magazine Corpus, Google Ngram Viewer, BYU Corpora, NYT Chronicle, Bookworm’s Chronicling America
- Publish a blog post discussing what you found when you explored your topic. How does this “model” or trend illustrate a historical event or era. Do the patterns tell you anything interesting? Any surprises? Please embed a screenshot or an image of the graphs you used to help you answer this question.
Last updated: November 19, 2015 at 18:30 pm