RECOMMENDED: The Joy of Topic Modeling

Matt Burton, graduate student at the University of Michigan School of Information, provides an accessible introduction to topic modeling. Aimed at beginners (though useful for everyone), the article unpacks the meaning of the terms used in topic modeling, such as model, word, document, topic, tokenization and stemming. For example, At the start of any text ...

RECOMMENDED: The Poetics of Non-Consumptive Reading

Building off of the amicus brief filed by Matthew Jockers, et al. in  Authors Guild vs. Google,  Mark Sample (George Mason University) has written a provocative post urging digital humanists to think critically about what it means to frame non-consumptive use–text-mining, topic modeling, etc.–as “non-expressive.” As the brief’s abstract explains: The brief argues that, just ...

RECOMMENDED: U.S. Open Data Policy

On May 9, 2013, the U.S. government issued Executive Order 13642, declaring that “the default state of new and modernized Government information resources shall be open and machine readable.” The announcement coincided with a memorandum outlining the creation of an open data policy that requires government agencies “to collect or create information in a way ...

RECOMMENDED: #dhpoco Open Thread

The Digital Humanities as a Historical “Refuge” From Race/Class/Gender/Sexuality/Disability? Sparked by David Golumbia’s recap of the “Dark Side of the Digital” conference (#c21dsd) at the University of Wisconsin-Milwaukee, Postcolonial Digital Humanities posted an open thread on the issues of race, gender, class, sexuality, and disability in DH. The thread has generated over 150 comments, providing ...

RECOMMENDED: DH Genealogies and the Academy (Weekend Round-Up)

“I just got done with a good twenty-four hours of arguing with people online about digital humanities.” So begins Stephen Ramsay’s post, “DH Types One and Two,” written in response to a flurry of conversations that took place online over the weekend. In part a reaction to Daniel Allington’s “Managerial Humanities: or, Why the Digital ...

RECOMMENDED: The Digital Humanities Contribution to Topic Modeling

Elijah Meeks and Scott Weingart are guest editors for the latest edition of Journal of Digital Humanities, which is devoted entirely to topic modeling (Vol. 2, No. 1 Winter 2012). Topic modeling is a method of textual analysis that has gained popularity in the humanities in the last few years. It uses computer algorithms to ...

RECOMMENDED: OA in the USA

The White House, responding to a We the People petition from May 2012, announced Friday that federal agencies with more than $100 million in research will make federally funded research and data sets freely available to the public within 12 months of publication. The Fair Access to Science and Technology Research Act (FASTR), which contains ...