Killer Applications in Digital Humanities

The field of “Digital Humanities” has been plagued by a perceived neglect on the part of the broader humanities community. The community as a whole tends not to be aware of the tools developed by HC practitioners (as documented by the recent surveys by Siemens et al.),
and tends not to take seriously many of the results of scholarship obtained by HC methods and tools. This
problem has been noticed recently by a number of groups
focusing on issues regarding humanities tools, most
notably the Text Analysis Developers Alliance (Text
Analysis Summit, May 9-11, 2005 at McMasters
University) and IATH (Summit on Digital Tools for the Humanities, September 28-30, 2005, at the University of Virginia).
One possible reason for this apparent neglect is a
mismatch of expectations between the expected needs of audience (market) for the tools and the community’s
actual needs. A recent paper by Gibson on the development
of an electronic scholarly edition of _Clotel_ may
illustrate this. The edition itself is a technical masterpiece,
offering, among other things, the ability to compare
passages among the various editions and even to track word-by-word changes. However, it is not clear who among Clotel scholars will be interested in using this capacity or this edition; many scholars are happy with their print copies and the capacities print grants (such as scribbling in the margins or reading on a park bench). Furthermore, the nature of the Clotel edition does not lend itself well either to application to other areas or to further extension. It is essentially a service offered to the broader research community in the hope that it will be used, and runs a great risk of becoming simply yet
another tool developed by the DH specialists to be ignored.
Matthew Jockers has observed that much of the focus in humanities computing is on “methodologies, not
results.” (Bradley, 2005). This paper argues for a focus on deliverable results in the form of useful solutions to genuine problems, instead of simply new representations.
The wider question to address, then, is what needs the humanities community has that can be dealt with using HC tools and techniques, or equivalently what incentive humanists have to take up and to use new methods. This can be treated in some respects like the computational
quest for the “killer application” -- a need of the user group that can be filled, and by filling it, create an acceptance
of that tool and the supporting methods/results. For
example, MS-Word and similar software has revolutionized
writing, even for non-specialists, to the same degree that Email has revolutionized communication and the World Wide Web has revolutionized publication. They have not only empowered non-specialists to do more, but also created inspiring opportunities for further secondary
research in extending the capabilities of these software tools. Digital Humanities needs a “killer application” -- a Great Problem that can both empower and inspire.
Three properties appear to characterize such Great
Problems. First, the problem itself must be real, in the sense that other humanists (or the public at large) should be interested in the fruits of its solution. Second, the
problem must be interesting, in the sense that the solution
is not obvious and the process of solving it will add
materially to human knowledge. Third, the problem itself
must be such that even a partial solution or an incremental improvement will be useful and/or interesting.
As a historical example of such a Problem (and the
development of a solution), consider the issue of resource
discovery. With the advent of the Web, billions of resources are now broadly available, but no one knows how to find
them. Traditional solutions (journal publications, citation indices, etc.) are no longer adequate as publication can happen through informal channels. Google provides
a partial solution to this problem by automatically
searching and indexing “the Web,” specifically to solve the general problem of finding stuff. At the same time, its algorithms are demonstrably inadequate both in terms of accuracy and in what it can search, leaving much room for incremental development -- but the partial solution that exists has still revolutionized scholarship, and created
a huge economic opportunity precisely to extend and
improve the solution.
To the three criteria above can thus be added an additional, more political aspect of any proposed “killer app.” Any proposed application should be extremely user-friendly, possibly even at the expense of complete generality -- the Perfect should not be the enemy of the Good, especially if the Perfect system is unusably general.
I have argued elsewhere that a possible candidate
for such a killer app would be authorship attribution: determining who (if anyone) from a candidate pool of authors wrote a particular document under discussion. This question is obviously of interest, for example, to scholars who wish either to validate a disputed authorship,
or for authors wishing to investigate if a document of
unknown authorship (say, an unsigned political pamphlet)
can be assigned to a known author (and help illuminate
some political views). Less obviously, “questioned
documents” are often extremely important in a legal and
forensic environment -- but traditional forensic analysis, such as handwriting, cannot address questions about (e.g.) born-digital documents, transcriptions, purported copies, and so forth. At the same time, enough papers have been published recently to demonstrate a strong interest in the problem from a humanities standpoint -- and even an analysis that is not strong enough to be conclusive prove can still suggest lines and approaches for further investigation and scholarship.
Another candidate that has been argued elsewhere is automatic back-of-the-book indexing. A third, discussed
at the recent IATH summit, is an automatic tool for
annotating fully-electronic multimedia documents. These
are difficult problems, and a full solution will involve (and illuminate) many subtle aspects of human cognition
and of the writing process. At the same time, other
scholars will be grateful for the results -- on the one hand, by relieving them of the difficult and expensive burden of generating indices for their own works, and on the other by supporting them in the ability to read and
annotate electronic documents in the way they traditionally
interact with paper.
It would be to the overall benefit to the DH community to
focus at least some effort and resources on the identification
and solution of such Great Problems and on the
development of such killer apps. The apparent alternative is the status quo, where digital research tools are brilliantly developed, only to languish in neglected disuse by the larger community.