WVU Libraries is offering three Research Commons workshops on using text mining with HathiTrust, a repository of more than 17 million digitized items. This massive collection of text is available for computational text mining, primarily through the tools and services of the HathiTrust Research Center. This half-day workshop will be held Nov. 5 from 9 a.m. to noon in the Downtown Campus Library, Room 2036. Registration is required.
The first workshop, “HathiTrust’s Data and Analysis Tools for Text Mining Research,” will be conducted by a Hathitrust representative who will provide an introduction to the text data and computational tools of HathiTrust.
Attendees will gain hands-on experience with these data and tools in order to become more familiar with the opportunities for research HathiTrust makes available. The workshop will include a characterization of the data available and hands-on activities with HTRC’s Extracted Features dataset and secure research environments.
Also, “Data and Donuts: Text Mining with HathiTrust and Python,” an introductory text mining workshop, will demonstrate common methods and tools used in this area of scholarship.
Participants will get hands-on experience using the text analysis tools provided by the HTRC and using command line to run basic text analysis with PythonAnywhere. There will be two opportunities to attend this free workshop: Nov. 8 from 2-3:30 p.m. in the Downtown Campus Library, Room 136; and Nov. 14 from 2-3:30 p.m. in the Evansdale Library, Room G16.
No experience is necessary, but prior exposure to text analysis concepts would be beneficial. For more information, visit HathiTrust.org or analytics.HathiTrust.org.