The TORCHLITE project is hosting a hackathon May 21-23, 2024 in Champaign, Illinois for researchers and programmers interested in text analysis and data mining/visualization using HathiTrust Research Center tools. The hackathon deliverables include data visualizations, Jupyter notebooks, applications, and creative uses for its new tools. Participants who are selected to attend will receive up to $1,000 in reimbursements for travel and accommodations.

More about the TORCHLITE project from the website:

The HathiTrust Research Center’s “Tools for Open Research and Computation with HathiTrust: Leveraging Intelligent Text Extraction” (TORCHLITE) . . . project leverages HTRC’s new Extracted Features API. The Extracted Features API allows programmatic access to metadata and annotated token data (aggregated at the page level) for more than 17 million volumes from the HathiTrust Digital Library collection, including in‑copyright material. This robust dataset includes all kinds of useful metadata and data about individual books, which can be leveraged to create interesting visualizations and applications. HTRC is currently developing visualizations that map author location data, publication dates, and word frequency.

Register to participate in the link on the website by March 1, 2024.


dh+lib Review

This post was produced through a cooperation between Mimosa Shah, Abbie Norris-Davidson, Kayla Abner, and Vera Zoricic (Editors-at-Large), Hillary Richardson and Rachel Starry (Editors for the week), Claudia Berger, Nickoal Eichmann-Kalwara, Linsey Ford, and Pamella Lach (dh+lib Review Editors), and John Russell (Editor in Chief).