Thursday, November 8, 2018
11:00 am - 12:00 pm
247 Hesburgh Library, Navari Family Center for Digital Scholarship
Text mining, a process for extracting information from unstructured text, requires everyday files (PDF, Word, HTML, etc.) to be transformed into plain text files. Once your files are in a plain text format (no bold, no italics, no underlining, etc.) they are ready for automated processing and computer analysis.
This hands-on workshop will demonstrate and facilitate the use of a free Java-based program called Tika that can do this work. More specifically, this workshop will help attendees install Tika and teach them how to use it to convert just about any file into plain text, with hopes that they will leave with the knowledge and confidence to use a myriad of text mining services available on the 'Net.
Open to all graduate and undergraduate students, postdocs, faculty and staff.
Digital Initiatives Librarian
emorgan@nd.edu
Eric Morgan is the Digital Initiatives Librarian in the Navari Family Center for Digital Scholarship. His current work focuses on assisting faculty and students with text mining and analysis. Though his work involves extensive computing expertise, Eric considers himself to be a librarian first, and a computer user second. His professional goal is to discover new ways to use computers to provide better library service. His research interests have included information retrieval, expert systems, and automated personalization.
MIS, 1987, Drexel University; B.A. Philosophy, 1982, Bethany College
For more information: http://www.nd.edu/~emorgan/
Julie Vecchio
Interim Co-Director, Navari Family Center for Digital Scholarship
250I Hesburgh Library
