Text Analysis for Digital Health Humanities: Using HTRC Data and Tools

Data from the more than 17.5 million volume HathiTrust Digital Library collection is made available for computational analysis primarily through the tools and services of the HathiTrust Research Center (HTRC). This workshop will provide a deeper dive into working with data derived from HathiTrust collection materials, including Extracted Features (metadata, derived text features, text as tokens) and full text from the publicly available UCSF University Publications collection, which documents histories of health sciences teaching, learning, and student activities from 1864-2009. Learners will be oriented to the characteristics of this data, how to access it, and how to conduct analysis with it using HTRC tools and services. The workshop will feature hands-on opportunities to learn and apply Python coding for text analysis.

A companion session on Friday, May 19 (10am-12pm PDT), HathiTrust Research Center (HTRC) Data and Tools for Digital Health Humanities: An Overview includes opportunities to learn about finding health related resources in HathiTrust, curating these into collections, finding or establishing a textual corpus for your research, and HTRC tools for exploring and analyzing text as data.