Resources for hands on DH workshop, February 2018
- Access Google Fusion Tables here
- Download Mallet here
- Get OpenRefine here
- #FutureMuseum documents derived from http://museum-id.com/the-futuremuseum-project-what-will-museums-be-like-in-the-future-essay-collection/
- Worksheets and slides above
- Discovery has an API which includes a sandbox allowing you to experiment with making different calls.
- One of our Digital Archivists, David Underdown, has published some simple Python scripts for interacting with the API.
- Our blog is a good source for a wide range of scholarship relating to our collections. In these posts Dr Richard Dunley introduces working with data from Discovery and then develops the analysis using 17th century prize papers. I discuss topic modelling Cabinet Papers here.
- 20,000 images on Flickr
- Collections and other images relating to The National Archives in Wikimedia Commons
- Matthew Jockers imagines Jane Austen and Herman Melville meeting at a buffet as an analogy to help understand topic modelling.
- Miriam Posner has a good introduction to interpreting topic model results
- The science of reading topic models is the subject of a 2009 paper by Chang et al. A presentation of their results is additionally available.
- I'm sure it's been mentioned repeatedly but The Programming Historian really is an excellent resource.