Coffee & Code: Getting started with text analysis using the HathiTrust Research Center
Details: Progressively greater access to digitized books and documents is creating opportunities for researchers to ask new data-driven questions about history, cultural trends, and literary and linguistic change. These research questions interrogate the textual human record at scales that can only be addressed algorithmically or quantitatively. The HathiTrust is a consortium of research libraries, and its digital library currently contains over 14 million items. The HathiTrust Research Center (HTRC) seeks to make this very large collection accessible for non-consumptive research via algorithmic text analysis. This session will introduce attendees to the HTRC’s tools and services, including how to execute algorithms against user-created sub-collections of text, how to use the HathiTrust+Bookworm tool for lexical trend discovery, and how to perform text analysis using HTRC-developed infrastructure and datasets.
Instructor: Eleanor Dickson (HTRC Digital Humanities Specialist, University of Illinois at Urbana-Champaign)
Note: Eleanor will be joining us virtually. This is a hands-on session. Computers will be available or you may bring your own laptop.
Related LibGuide: Text & Data Mining by Enid Karr
- Monday, October 17, 2016
- 1:00pm - 2:00pm
- Digital Studio (Rm. 205)
- Chestnut Hill Campus