An archived version of a webinar offering strategies and tools for text and data mining for scholars in the social sciences and humanities has been posted by the Center for Research Libraries.
Peter Leonard, director or the Digital Humanities Laboratory and Lindsay King, assistant director of the Haas Arts Library, both at the Yale University Library, are the presenters in the 80-minute webinar, which appears below. Leonard explains how three trends – heaps of digitized source material now coming available, the software that allows plowing through this data, and improvements in technique and technology – are spurring interest in data mining. King, meanwhile, looks at a particular project — Robots Reading Vogue — as a demonstration of these research applications.
As Leonard told the Yale Daily News last fall, ““We think of libraries as buying physical books, and Yale libraries will never stop. But we also want to develop ways of making sense of large cultural collections.”
The CRL has also held two webinar on mining Big Data in economics.
The first, from October 2014, was hosted by Robin Bew, managing director of the Economist Intelligence Unit, and Chris Pearce, who directs the unit’s global data operations. They examined how their employer supports the complex global data needs of major academic research projects in the field of international trade and economics.
The second, from February 2015, with presenters Bernard Reilly, from the Center for Research Libraries, and Bobray Bordelon of Princeton University, looked both at trends emerging in publishing financial and economic data, particularly from the developing world, and at how the balance has shifted between open access and commercial publication of international data.