Kerry Kilner

Searching for My Lady’s Bonnet: discovering poetry in the National Library of Australia’s newspapers database

AustLit is a major Australian cultural heritage database and the most comprehensive record of a nation’s literary history in the world. In this article we will present the successful results of a project addressing the challenge of discovering and recording creative writing published in digitized historical Australian newspapers, provided by the National Library of Australia’s Trove service. As a first step in identifying creative writing, we developed an automated method for identifying articles that are likely to be poems by searching for a number of signals embedded in articles. When this work began, AustLit contained more 10,200 bibliographical records for poems published between 1803 and 1954 (75% prior to 1900) with links to the full text in 115 different newspaper. The aim of the project was to expand this number of bibliographical records in AustLit and provide a foundation for analysing the importance of poetry in newspaper publishing of the period. Taking advantage of Ted Underwood’s (Getting Everything you Want from HathiTrust , and Open Data ( ): The Stone and the Shell, Underwood blog posts (Both accessed 27 October 2015), 2012) work with seventeenth- and eighteenth-century full text in the HathiTrust collection, we trained a naive Bayesian classifier, modifying code from Daniel Shiffman (Bayesian Filtering. (accessed 27 October 2015), 2008) and Paul Graham (A Plan for Spam. (accessed 27 October 2015), 2002) and improving the quality of Optical Character Recognition (OCR) by using the overProof correction algorithm. We have been able to successfully identify large numbers of poems in the newspapers database, greatly expanding AustLit’s coverage of this important literary form. After suitable training of the classifier, we were able to successfully identify 88% of the newspaper articles that a knowledgeable human would classify as ‘poetry’. Our results have encouraged us to consider enhancing and extending the techniques to aid the identification of other forms of literature and criticism.

The American Literature Scholar in the Digital AgeAmy E. Earhart, Andrew Jewell (eds).

Contemporary scholarly pursuits using digital technology in American literary studies is the uniting theme in this collection of essays, expertly edited by Earhart and Jewell. This exciting book explores the opportunities, potentials, and issues that scholars now face in an environment where the outcomes of research are no longer ‘limited to the print-confined genres of ‘‘essays’’ or ‘‘books’’ or ‘‘chapters’’ ’ (p. 2). In a wide ranging survey of current practice, Earhart and Jewell present a range of projects and activities that can ‘take the form of sprawling ‘‘thematic research collections,’’ algorithms that derive consequential meaning from enormous text corpora, or interactive visualizations of data derived from selected works of literature, . . . 3-D visualizations, maps, images, movies, songs, spoken word, blogs, wikis, games and more’ (p. 2). The diversity of scholarly approaches to engaging digitally with American literary and print culture is well documented here, as is the range of infrastructural issues that form a part of the current intellectual and institutional landscape. A central thread running through many of the essays is whether the use of digital methodologies in scholarly work actually enables new insights into, and interpretations of, literary works and literature’s place in society. There is ample evidence given here that access to literary content in digital form, combined with appropriate tools to undertake analytical work can, indeed, enable scholars to use texts differently and arrive at interesting and new insights into the texts and contexts of literary culture. One interesting example of this transformative possibility is described in Edward Whitley’s informative essay, ‘Visualizing the Archive’, in which he discusses Tanya Clement’s use of textual analytics and visualization techniques to undertake a distant reading of Gertrude Stein’s notoriously difficult novel, The Making of Americans. Clement’s approach allowed her to make a compelling case for reading Stein’s novel as ‘a deeply philosophical reflection on the life of an American family’ (p. 191). By discovering ‘identifiable patterns of linguistic repetition’ she rehabilitates the novel from its position as a fundamentally flawed novel or a failed attempt at experimental poetics. She makes the case that the techniques used for this analysis reveal a narrative structure that traditional close reading practices would miss. Another bright thread running through the collection is the desire to ensure that the serendipity of discovery, a treasured experience of all researchers, is not lost by the wholesale move to a digital research environment where the use of digital objects necessarily replaces, for a range of valid reasons, the use of physical objects. A number of the essays reflect a slight anxiety that selective digitisation, a necessity for some projects, has the potential to reduce those opportunities for stumbling upon something that totally changes the course of a researcher’s work. For example, in discussing the Walt Whitman Archive’s attempt to identify and make available all of Whitman’s poems published in periodicals, Susan Balasco acknowledges that the digitization process used in that project, which selects only the pages upon which poems appear, means that much of the context of publication is obscured. The experience of leafing through a print version of a periodical, she notes, provides context and juxtaposition that can deepen a researcher’s comprehension of the author’s work, associations, and place within the public sphere. This decontextualization of literary works may make for poorer, or at least blander, scholarship as a result. The issue of selective digitization relates peripherally to the problematic potential for digitization projects to reinscribe the literary canon and to further ghettoize minority literatures and writers. It would seem that in order to replicate the opportunities for serendipity and the access to both major and minor works and writers, mass, indiscriminate digitization projects are desirable. Among the archives discussed here are those providing access to literary and other material related to Reviews