What insights, avenues for research, or new tools might we discover by experimenting with computational methods on material from library collections? In partnership with Princeton University Library, the CDH invites research software engineers and programmers for a one-day hackathon on the Latin America Ephemera collection, which includes around 12.2k published items. The library will provide dirty OCR text for the content, in addition to IIIF metadata and images that are already available. Exploration possibilities include named entity recognition, classification, automated image processing, machine learning, topic modeling, and data visualization/sonification/physicalization. High-performance computing resources will be available for use by participants, with assistance from Research Computing. Light breakfast, lunch, and afternoon refreshments will be provided.
RSVP is required for this event. Interested parties should contact CDH developer Nick Budak (email@example.com) for more information.