Digging Into Data, Day 2: Making Tools and Using Them
Chronicle of Higher Education,, June 12, 2011, By Jennifer Howard
Washington-The age of innovation in digital tool-making is slowing down, making room for users of those tools to take the creative lead. That's what participants in the 2011 Digging Into Data Challenge Conference heard from one keynote speaker, Tom Jenkins, executive chairman and chief strategy officer of the software company Open Text. Throughout history, he said, "the application is far more profound" than the original idea.
The meeting, which concluded here Friday, featured eight digital-humanities research projects that showed how creative scholars have gotten in combining big data and digital tools. The eight projects were winners in the first Digging Into Data competition , held in 2009 to stimulate innovative digital work in the humanities and social sciences. (A second competition has just been announced.) An international group of grant-making organizations, including the National Endowment for the Humanities and research councils in Canada and Europe, supports the program.
During the two-day conference, linguists, musicologists, historians, and computer scientists showed off the results of playing, in a serious way, with enormous amounts of data. All the projects work on a scale that used to be seen only in the sciences.
One project, "Mining a Year of Speech," pulled together year's worth of spoken English-at least two terabytes' worth-collected "in the wild," meaning not recorded in labs but taken from real-world conversations, news broadcasts, and other sources. The researchers demonstrated ways in which the huge corpus can be mined: to track varying emphases in pronunciations of a certain phrase, for instance, on a scale and at a speed that would be impossible in traditional linguistic research.
Gregory PS: The winning projects are
- Digging into Image Data to Answer Authorship Related Questions
- Digging into the Enlightenment: Mapping the Republic of Letters
- Mining a Year of Speech
- Structural Analysis of Large Amounts of Music Information
- Harvesting Speech Datasets for Linguistic Research on the Web
- Using Zotero and TAPoR on the Old Bailey Proceedings: Data Mining with Criminal Intent
- Towards Dynamic Variorum Editions
- Railroads and the Making of Modern America-Tools for Spatio-Temporal Correlation, Analysis, and Visualization