This workshop will introduce attendees to the HathiTrust Research Center’s tools and services for utilizing the massive HathiTrust Digital Library in computational text analysis. The HTRC leverages the scope and scale of HathiTrust Digital Library’s holdings to allow researchers the opportunity to perform text data mining. The workshop will be broken into two sessions, morning and afternoon. Topics that will be covered include:

• How the HTRC makes HathiTrust volumes available for text mining.
• How to identify relevant volumes and build worksets (collections) of content for analysis.
• How to use HTRC off-the-shelf tools for text analysis and visualization.
• How to access HathiTrust data and metadata via provided APIs, request procedures, and open datasets.

The workshop will be led by Eleanor Dickson, ‎HathiTrust Research Center Digital Humanities Specialist at the University of Illinois, and Leanne Nay, Digital Engagement Librarian at the University of Indiana.

Registration is required for the workshop: http://nyu.libcal.com/event/3569768

There will be a follow up individual consultations session on Tuesday, October 17th, 9:00 am for participants in the workshop who need further guidance on a specific HTRC project that they are engaged with.

For those who are currently conducting research using text-as-data and data-mining projects using HathiTrust’s holdings, we will be hosting a lightning-talk session over the workshop lunch hour break on Monday, 12-2 pm. If you are interested in presenting a brief, 5-minute overview of your HTRC-based research, please indicate this on the registration form. The workshop will try to accommodate as many presenters as possible given time restraints.

Please contact digital.scholarship@nyu.edu with any questions.