The paper covers why the software exists, how we developed it, what projects it builds on & other related work, and example use-cases to show its potential.

This is the first software paper published in Computational Humanities Research journal, part of the series “Missing Data in the Humanities.”

Good turn out for @dhtech-community.bsky.social symposium at #DH2025

Nice mix of folks doing technical work and interested in technical talks.

#dhtech #DH2024 blog post challenge: write or draft a blog post for the dhtech site sometime this week and get one of these cute hippos
dh-tech.github.io

Speculation! We implemented recommendation systems using known Shakespeare and Company borrowing to predict missing borrowing activity.

Hemingway is our test case: his early membership borrowing records don’t survive, lots of documentation to check our results (letters, book catalogs).

We used Copia by Mike Kestemont, @folgertk.bsky.social et al. on Shakespeare and Company lending library books, treating each borrow as a “sighting” of a title. We estimate the data includes 64-76% of books despite only ~26% of borrowing activity.

We calculated a “borrowing capacity” based on known subscription limits & discovered members went over subscription limits and Sylvia Beach got more lenient in later years. We compare to a handwritten tally from 1931: 75 books out is 2x our estimate!

We use time series forecasting to estimate missing membership activity (subscriptions, renewals, reimbursements) and members and conclude that Shakespeare and Company Project datasets include 93% of membership activity and 96% of members.