I wonder if it wouldn’t be interesting to just pick a data set and try, collaboratively, to learn something from it? It would be interesting to see how others approach a problem from the process perspective: which questions asked, which tools used, etc. I don’t have a particular data set in mind, except that the APS just released “Benjamin Franklin Post Office Records,” which looks intriguing. Here: https://diglib.amphilsoc.org/islandora/compound/franklin-post-office-book-1748-1752#page/1/mode/1up and Here: https://github.com/AmericanPhilosophicalSociety/Historic-Postal-Data .

Susan