Digital humanities scholars receive Mellon support

Thomas Mullaney
Thomas Mullaney

The Andrew W. Mellon Foundation, which supports scholarly initiatives in the humanities and arts, has awarded $175,000 to several Stanford faculty members to bridge the technological gap between Asian studies and the digital humanities.

The award will finance a Sawyer Seminar, a pop-up research center that will bring together scholars of Asia across the humanities and sciences at Stanford.

Its recipients are as versatile as the project’s scope: from the humanities are THOMAS MULLANEY, associate professor of history; JAROSLAW KAPUSCINSKI, associate professor of music; and DAVID MCCLURE, lead software developer at the Stanford Literary Lab. Recipients from the sciences are DAN JURAFSKY, professor of linguistics and computer science, and JULIE SWEETKIND-SINGER, head of the Banner Earth Sciences Library & Map Collections.

The Sawyer Seminar will address a problem that bedevils Asian studies: the scarcity of digital tools and technologies to analyze text in non-Latin languages.

“An impartial view of Digital Humanities (DH) scholarship in the present day reveals a stark divide between ‘the West and the rest,’” said Mullaney. “Far fewer large-scale DH initiatives have focused on Asia and the non-Western world than on Western Europe and the Americas.”

Buttressed by the rise of data science, faculty across humanities fields have harnessed search algorithms and optical character recognition (OCR) to conduct research on an unprecedented scale. Petabytes, not pages, are now the unit of analysis. Yet the majority of these tools only handle Latin script.

“Digital databases and text corpora – the ‘raw material’ of text mining and computational text analysis – are far more abundant for English and other Latin alphabetic scripts than they are for Chinese, Japanese, Korean, Sanskrit, Hindi, Arabic and other non-Latin orthographies,” Mullaney said. Troves of unread primary sources lie dormant because no text mining technology exists to parse them. On Google and other search engines, for example, Boolean queries (using “AND” or “NOT”) written in Chinese characters often retrieve unusable results.

Mullaney and his colleagues will chip away at this technological barrier by hosting public lectures on the digital technologies in Asian studies, holding hands-on workshops about non-Western digital humanities and convening small groups for Sawyer Seminar residents and Stanford researchers.

This collaboration aims to cultivate a community of scholars that, for Mullaney, “stands to benefit far more greatly by engaging in unconventional and unprecedented forms of cross-regional and cross-linguistic exchange.”

An incubator for new technologies, the Sawyer Seminar will also gather dozens of digital humanists focused on particular regions and languages across Asia. A specialist in Chinese history, like Mullaney, shares many of the same frustrations with scholars who conduct digital humanities research in Arabic, Persian or Sanskrit. The same is true of experts on different historical periods, giving a historian on the Han dynasty reason to strike up a conversation with a specialist in Ottoman poetry.

A defining feature of the seminar is that researchers will learn to engineer the technologies they use. Often, though not always, scholars learn how to use tools in the digital humanities — text mining or network analysis — without developing sufficient proficiency to build and modify their own. But the Sawyer Seminar will train participants to enhance and even create research technologies themselves.

First established by the Mellon Foundation in 1994, Sawyer Seminars support research into the historical and cultural underpinnings of current events. Their aim is to promote comparative study of a subject in the humanities and social sciences that applicants could not otherwise pursue. Seminars cut across disciplines and fields, drawing together faculty, postdoctoral fellows, graduate students and researchers from the recipients’ home institutions and others nearby.