Tanya E. Clement

Discovering interesting usage patterns in text collections: integrating text mining with visualization

This paper addresses the problem of making text mining results more comprehensible to humanities scholars, journalists, intelligence analysts, and other researchers, in order to support the analysis of text collections. Our system, FeatureLens1, visualizes a text collection at several levels of granularity and enables users to explore interesting text patterns. The current implementation focuses on frequent itemsets of n-grams, as they capture the repetition of exact or similar expressions in the collection. Users can find meaningful co-occurrences of text patterns by visualizing them within and across documents in the collection. This also permits users to identify the temporal evolution of usage such as increasing, decreasing or sudden appearance of text patterns. The interface could be used to explore other text features as well. Initial studies suggest that FeatureLens helped a literary scholar and 8 users generate new hypotheses and interesting insights using 2 text collections.

What's being said near “Martha”? Exploring name entities in literary text collections

A common task in literary analysis is to study characters in a novel or collection. Automatic entity extraction, text analysis and effective user interfaces facilitate character analysis. Using our interface, called POSvis, the scholar uses word clouds and self-organizing graphs to review vocabulary, to filter by part of speech, and to explore the network of characters located near characters under review. Further, visualizations show word usages within an analysis window (i.e. a book chapter), which can be compared with a reference window (i.e. the whole book). We describe the interface and report on an early case study with a humanities scholar.

Toward a Notion of the Archive of the Future: Impressions of Practice by Librarians, Archivists, and Digital Humanities Scholars.

With this piece, we seek to interrogate the sites at which library, archival, and scholarly work occurs in order to consider the changing nature of the future of the archive. First, we consider the work of the archive from the perspective of the long-standing tradition of scholarly publication and scholarly editing in archives and libraries. Second, we introduce interviews with five leading humanities scholars and practitioners, who discuss the work that is involved in producing scholarship in archives and libraries. Finally, we explore the topics and themes that surface from the interviews, including centralized digital repositories, open-source methods and applications, and community building. This conclusion gives insight into theories and modes of practice that are developing and shaping notions of the archive as a site of collaborative work among archivists, librarians, and humanists, who are constantly negotiating their shifting roles in the stewardship of the archives of the future.

Methodologies in the digital humanities for analyzing aural patterns in texts

Increased access to large-scale repositories of text begs questions about how scholars can use such repositories in their research. It is essential that iSchools are aware of tools being created in the Digital Humanities since the processes and tools that are being developed by this transdisciplinary community are changing the preservation and curation of humanities data. This paper will discuss a use-case study that uses theories of knowledge representation and research on phonetic symbolism to develop analytics and visualizations that help users examine aural patterns in text. This work includes (1) identifying OpenMary as a base analytic; (2) creating a routine in MEANDRE (a semantic-web-driven data-intensive flow execution environment) that produces a tabular representation of the data for predictive modeling; and (4) developing an interface (ProseVis) for seeing these comparisons across text collections.

Connecting theory and practice in digital humanities information work

The omnipresence and escalating efficiency of digital, networked information systems alongside the resulting deluge of digital corpora, apps, software, and data has coincided with increased concerns in the humanities with new topics and methods of inquiry. In particular, digital humanities (DH), the subfield that has emerged as the site of most of this work, has received growing attention in higher education in recent years. This study seeks to facilitate a better understanding of digital humanities by studying the motivations and practices of digital humanists as information workers in the humanities. To this end, we observe information work through interviews with DH scholars about their work practices and through a survey of DH programs such as graduate degrees, certificates, minors, and training institutes. In this study we focus on how the goals behind methodology (a link between theories and method) surface in everyday DH work practices and in DH curricula in order to investigate if the critiques that have appeared in relation to DH information work are well founded and to suggest alternative narratives about information work in DH that will help advance the impact of the field in the humanities and beyond.

The Ear and the Shunting Yard: Meaning Making as Resonance in Early Information Theory

Our cultural institutions host large collections of audio recordings comprising important cultural artifacts. Some of these recordings date back to the nineteenth century and up to the present day. These recordings include music but also poetry readings, field recordings, and presidential speeches and phone calls, as well as the only recordings of languages, oral traditions, and voices that we no longer remember. We have dedicated significant resources to digitizing these collections, yet, even digitized, these artifacts are only marginally accessible for listening and almost completely inaccessible for new forms of access and scholarship. In order to discover convergences in seemingly divergent theories that may guide how we build information infrastructure around our sound heritage, this article considers how early information theory, much of which was crafted within the context of developing communication and sound technologies, can provide a framework for thinking through how to build an information infrastructure that facilitates inquiry with digital audio collections in the humanities.

Measured Applause: Toward a Cultural Analysis of Audio Collections

Applause is a significant cultural marker in recorded performances. In poetry performances, applause can be a means by which an audience can indicate its response to a speaker’s performance or to the audience in general; a means for expressing elation and appreciation or, perhaps, dismay; and a way to engage indialog with a poem itself and affect its mode of meaning making.

High Performance Sound Technologies for Access and Scholarship (HiPSTAS) in the Digital Humanities

Currently there are few means for humanists interested in accessing and analyzing spoken word audio collections to use and to understand how to use advanced technologies for analyzing sound. The HiPSTAS (High Performance Sound Technologies for Access and Scholarship) project introduces humanists to ARLO (Adaptive Recognition with Layered Optimization), software that has been developed to perform spectral visualization, matching, classification and clustering on large sound collections. As this paper will address, this project has yielded three significant results for developing tools that facilitate machine learning with spoken word collections of keen interest to the humanities: (1) an assessment of user requirements; (2) an assessment of technological infrastructure needed to support a community tool; and (3) preliminary experiments using these advanced resources that show the efficacy, both in terms of user needs and computational resources required, of using machine learning tools to improve discovery with unprocessed audio collections.