Spring 2009

How do we know when we're done? This cluster of articles explores completion and incompletion in the digital humanities from a variety of perspectives.

The word finish can mean two things that have quite different implications for large-scale humanities computing projects: "to bring to completion; to make or perform completely; to complete" and also "to perfect finally or in detail; to put the final and completing touches to (a thing)." The word finish is just not part of the deal for the Linguistic Atlas Project in either sense. However, granting agencies must ask what do you want money for this time? and, from this viewpoint, the Atlas Project consists of a series of particular tasks or experiments, each one of which is capable of being finished in both senses of the word. This paper discusses the reality of funding, deadlines, and deliverables, as they relate to the sequence of tasks that make up the larger Atlas Project. There are no once-and-done, permanent solutions. The largest humanities computing projects require continuing care and maintenance, and the best way forward is to create some sort of stable institutional setting for large projects that will provide continuity and baseline resources for the work.

Since the early 1990s, theorizing in the digital humanities has often celebrated open-endedness and incompletion as inherent qualities of digital work. But a scholarly publisher undertaking preparation and sale of digital objects cannot altogether dispense with traditional notions of deadlines and completion if those publications are to enter the dual marketplaces of peer review and institutional purchase. The Electronic Imprint of the University of Virginia Press was funded in 2001 with the goal of bringing born-digital scholarly projects under the aegis of the same review and marketing system that applies to books. In this article I describe how we defined the criteria for done-ness in creating two very different projects, a born-digital edition of Herman Melville’s Typee manuscript and a conversion of the letterpress Papers of George Washington into a digital edition. Our experience suggests that it is possible to categorize different genres of digital creations based on the extent to which intrinsic criteria for “done-ness” can be applied to them, and that decisions about completeness are always subject to extrinsic factors as well, such as budgetary constraints and the pressures created by competition and the evolution of standards.

The case of the Orlando Project offers a useful interrogation of concepts like completion and finality, as they emerge in the arena of electronic publication. The idea of doneness circulates discursively within a complex and evolving scholarly ecology where new modes of digital publication are changing our conceptions of textuality, at the same time that models of publication, funding, and archiving are rapidly changing. Within this ecology, it is instrumental and indeed valuable to consider particular tasks and stages done, even as the capacities of digital media push against a sense of finality. However, careful interrogation of aims and ends is required to think through the relation of a digital project to completion, whether modular, provisional, or of the project as a whole.

In this study, a corpus of 300 male-authored and 300 female-authored French literary and historical texts is classified for author gender using the Support Vector Machine (SVM) implementation SVMLight, achieving up to 90% classification accuracy. The sets of words that were most useful in distinguishing male and female writing are extracted from the support vectors. The results reinforce previous findings from statistical analyses of the same corpus, and exhibit remarkable cross-linguistic parallels with the results garnered from SVM models trained in gender classification on selections from the British National Corpus. It is found that female authors use personal pronouns and negative polarity items at a much higher rate than their male counterparts, and male authors demonstrate a strong preference for determiners and numerical quantifiers. Among the words that characterize male or female writing consistently over the time period spanned by the corpus, a number of cohesive semantic groups are identified. Male authors, for example, use religious terminology rooted in the church, while female authors use secular language to discuss spirituality. Such differences would take an enormous human effort to discover by a close reading of such a large corpus, but once identified through text mining, they frame intriguing questions which scholars may address using traditional critical analysis methods.

Machine learning and text mining offer new models for text analysis in the humanities by searching for meaningful patterns across many hundreds or thousands of documents. In this study, we apply comparative text mining to a large database of 20th century Black Drama in an effort to examine linguistic distinctiveness of gender, race, and nationality. We first run tests on the plays of American versus non-American playwrights using a variety of learning techniques to classify these works, identifying those which are incorrectly classified and the features which distinguish the plays. We achieve a significant degree of performance in this cross-classification task and find features that may provide interpretative insights. Turning our attention to the question of gendered writing, we classify plays by male and female authors as well as the male and female characters depicted in these works. We again achieve significant results which provide a variety of feature lists clearly distinguishing the lexical choices made by male and female playwrights. While classification tasks such as these are successful and may be illuminating, they also raise several critical issues. The most successful classifications for author and character genders were accomplished by normalizing the data in various ways. Doing so creates a kind of distance from the text as originally composed, which may limit the interpretive utility of classification tools. By framing the classification tasks as binary oppositions (male/female, etc), the possibility arises of stereotypical or lowest common denominator results which may gloss over important critical elements, and may also reflect the experimental design. Text mining opens new avenues of textual and literary research by looking for patterns in large collections of documents, but should be employed with close attention to its methodological and critical limitations.

The Encyclopédie of Denis Diderot and Jean le Rond d'Alembert was one of the most important and revolutionary intellectual products of the French Enlightenment. Mobilizing many of the great – and the not-so-great – philosophes of the 18th century, the Encyclopédie was a massive reference work for the arts and sciences, which sought to organize and transmit the totality of human knowledge while at the same time serving as a vehicle for critical thinking. In its digital form, it is a highly structured corpus; some 55,000 of its 77,000 articles were labeled with classes of knowledge by the editors making it a perfect sandbox for experiments with supervised learning algorithms. In this study, we train a Naive Bayesian classifier on the labeled articles and use this model to determine class membership for the remaining articles. This model is then used to make binary comparisons between labeled texts from different classes in an effort to extract the most important features in terms of class distinction. Re-applying the model onto the original classified articles leads us to question our previous assumptions about the consistency and coherency of the ontology developed by the Encyclopedists. Finally, by applying this model to another corpus from 18th century France, the Journal de Trévoux, or Mémoires pour l'Histoire des Sciences & des Beaux-Arts, new light is shed on the domain of Literature as it was understood and defined by 18th century writers.

A response to the Data Mining cluster, exploring the role of machine learning in textual study.