Alien Reading: Text Mining, Language Standardization, and the Humanities [Munch & Mull Digital Scholarship Discussion Group]
As part of its spring DH Workshop series, Duke Libraries’ Digital Scholarship Services is focusing several workshops on distant reading – a gentle way of describing what amounts to a frequently opaque and heavily computational approach to a uniquely human activity. Using computational methods to “read” texts is frequently met with skepticism by humanist scholars, if not outright antagonism, and even technology scholars have questioned whether these methods and tools, created in contexts and for purposes outside of humanistic study, can or should be so readily adopted.
In “Alien Reading: Text Mining, Language Standardization, and the Humanities,” from the 2016 edition of Debates in the Digital Humanities, Jeffrey Binder walks through the history of text mining and the humanities, particularly its growth beginning in the 1990s and the Latent Dirichlet Analysis (LDA) technique. His discussion of the motivations behind different techniques and tools, underlying mechanics, and subsequent adoptions and critiques, provides useful perspective on how we “read” digital texts, as well as a valuable foundation for exploring these concepts more closely in upcoming workshops on text mining in the humanities.
Munch & Mull is a Libraries-based discussion group that holds weekly, informal, brown-bag lunch conversations around issues, projects, methods, and trends in digital scholarship. All are welcome!
The current M&M schedule of talks is on the Digital Scholarship Services website, https://library.duke.edu/digital/events. For more information about upcoming discussions, join our listserv: https://lists.duke.edu/sympa/subscribe/munch-mull-digihum-reading-group.