publications

2023

1. JIS

   The Ripple Effect of Dataset Reuse: Contextualising the Data Lifecycle for Machine Learning Data Sets and Social Impact

   Park, Jaihyun,  and Cordell, Ryan

   Journal of Information Science Dec 2023

   Abs HTML

   Although there exists a rich literature on data lifecycle, a common framework for data lifecycle depicts reuse as the last stage. However, this framework fails to explain the complex lifecycle of machine learning (ML) data sets, which can have many different afterlives. Data sets for ML can be expanded to supplement previous research, and researchers can concatenate multiple data sets to develop new models. This study discusses ML dataset reuse through the lens of the data–information–knowledge–wisdom pyramid. In social science research, researchers might reuse data to analyse a new research question that is still in the context of the data domain. By contrast, research practices in ML, where researchers layer multiple data sets for training purposes, require us to ask whether the existing data lifecycle model, ending with ‘reuse’, is appropriate for explaining such an iterative and layered lifecycle. This study introduces one case of merging computer vision data set and natural language processing data set and two cases of applying ML models from outside of the ML community (hate speech detection and politeness detection) to justify a framework for a ML dataset lifecycle. Last but not least, this study proposes a ML dataset lifecycle and provides case examples to describe each stage.

2022

1. Material Cultures of the Digital

   Cordell, Ryan

   Dec 2022

   Abs HTML

   With the rise of digital technologies the number and diversity of related tools (such as phones, computers, 3-D printers, etc.) have markedly increased. This chapter examines how digital objects and other new technologies alter human experiences with the material world.

2. LT

   Closing the Loop: Bridging Machine Learning (ML) Research and Library Systems

   Cordell, Ryan

   Library Trends Dec 2022

   Abs HTML

   This article argues that if libraries are to take leadership in conversations about the ethics and application of machine learning (ML) to cultural materials, they must move beyond the "perpetual future tense" of most library ML proposals and experiments, narrowing the gap separating promises that ML will enhance discoverability for library materials and the library systems through which most users encounter those materials. Even as ML methods have grown more powerful, nuanced, and sophisticated, ambitious hopes that ML might help better identify and describe vast library collections have been largely unmet, at least from the perspective of library patrons, researchers, and students. To address this gap, the article argues that libraries and ML researchers should work together to develop iterative, experimental, and even speculative interfaces that allow users to explore collections through ML-derived patterns that can enhance library data while educating users about ML processes, decisions, and biases.

3. Newspapers and Periodicals

   Cordell, Ryan

   Dec 2022

   Abs HTML

   In a review of Graham’s Magazine published in the March 1, 1845 issue of The Broadway Journal, Edgar Allan Poe predicted of magazine literature, “[i]n a few years its importance will be found to have increased in geometrical ratio” because “[t]he whole tendency of the age is Magazine-ward.” Busy mid-century readers, speeding along in “the rush of the age,” required a medium that kept pace. “We now demand the light artillery of the intellect,” Poe insisted: “we need the curt, the condensed, the pointed, the readily diffused – in place of the verbose, the detailed, the voluminous, the inaccessible.”1 It can be difficult to pin down how seriously Poe took such declarations. Praise and ironic critique intertwine in his critical writings, as in subsequent paragraphs of this review, where he describes the engraving “Dacota Woman and the Assiniboin Girl” as “worthy of all commendation,” while another engraving in the same issue, “The Love Letter,” “has the air of having been carved by a very small child, with a dull knife, from a raw potato.”2 If Poe marks a genuine trend toward periodical forms of literature in the period, he also stages an ambiguous response to the trend, vacillating between praise and condemnation.

4. Material Cultures of the Digital

   Cordell, Ryan

   Dec 2022

   Abs

   With the rise of digital technologies the number and diversity of related tools (such as phones, computers, 3-D printers, etc.) have markedly increased. This chapter examines how digital objects and other new technologies alter human experiences with the material world.

5. Going the Rounds: Virality in Nineteenth-Century American Newspapers

   Cordell, Ryan C., Smith, David A.,  Mullen, Abby and 2 more authors

   Dec 2022

   Abs HTML

   Going the Rounds brings together literary, historical, and computational criticism to illuminate the extent, content, and character of information exchange in nineteenth-century US periodicals. Drawing on reprinted texts from the NEH-, Mellon-, and ACLS-funded Viral Texts Project at Northeastern University, Going the Rounds situates widely reprinted newspaper genres such as lists, scientific reports, recipes, travel accounts, and vignettes at the center of the period’s print culture. Drawing on methods such as text mining, geospatial analysis, and network analysis, the book offers a new, systemic account of information exchange in the nineteenth-century’s primary mass medium.

2020

1. Speculative Bibliography

   Cordell, Ryan

   Anglia Sep 2020

   Abs HTML

   Abstract

   This article proposes speculative bibliography as an experimental approach to the digitised archive, in which textual associations are constituted propositionally, iteratively, and (sometimes) temporarily, as the result of probabilistic computational models. Speculative bibliography is offered as a complement to digital scholarly editing, and as a direct response to the challenges of scale and labour that will make comprehensive editing of digital archives impossible. Rather than acting on specific, individual texts, a speculative bibliography enacts a scholarly theory of the text through a computational model, reorganising the archive to evidence a particular idea of textual relation or interaction. Such models, in which textual relationships are determined by formal, internal textual structures, constitute bibliographic arguments that can be verified, amended, extended, or contested on either humanistic or computational grounds.

2. LoC

   Machine Learning + Libraries

   Cordell, Ryan

   Jul 2020

   Abs HTML

   The report expertly frames machine learning and both its possibilities and its challenges. After defining machine learning and distinguishing it from the broader category of artificial intelligence (AI), Dr. Cordell describes the history of the use of these technologies in libraries and explores various approaches. Urging care and thoughtful implementation of machine learning, the report points out the risks and potential benefits for crowdsourcing, searchability of type and handwritten documents and audiovisual materials, collection management, conservation and preservation, and creative and artistic works. The report concludes with recommendations for responsibly implementing machine learning, improving access to data, developing infrastructure, and cultivating expertise.

2019

1. Teaching Humanistic Data Analysis

   Cordell, Ryan C.

   Jul 2019

2018

1. Kaleidoscopic Pedagogy: The Idea of a C19 Classroom Laboratory

   Cordell, Ryan C., Doyle, Benjamin,  and Hopwood, Elizabeth

   Nov 2018
2. A Research Agenda for Historical and Multilingual Optical Character Recognition

   Smith, David A,  and Cordell, Ryan

   Nov 2018

   HTML

2017

1. BH

   "Q i-Jtb the Raven": Taking Dirty OCR Seriously

   Cordell, Ryan

   Book History Nov 2017

   Abs HTML

   Abstract:This article argues that scholars must understand mass digitized texts as assemblages of new editions, subsidiary editions, and impressions of their historical sources, and that these various parts require sustained bibliographic analysis and description. To adequately theorize any research conducted in large-scale text archives—including research that includes primary or secondary sources discovered through keyword search—we must avoid the myth of surrogacy proffered by page images and instead consider directly the text files they overlay. Focusing on the OCR (optical character recognition) from which most large-scale historical text data derives, this article argues that the results of this "automatic" process are in fact new editions of their source texts that offer unique insights into both the historical texts they remediate and the more recent era of their remediation. The constitution and provenance of digitized archives are, to some extent at least, knowable and describable. Just as details of type, ink, or paper, or paratext such as printer’s records can help us establish the histories under which a printed book was created, details of format, interface, and even grant proposals can help us establish the histories of corpora created under conditions of mass digitization.

2. AmP

   "Fugitive Verses": The Circulation of Poems in Nineteenth-Century American Newspapers

   Cordell, Ryan,  and Mullen, Abby

   American Periodicals: A Journal of History & Criticism Mar 2017

   Abs HTML

   This article proposes a nineteenth-century term, “fugitive verses,” as a conceptual framework for grappling with the textual and authorial fluidity of newspaper poetry, a genre that simultaneously reflected the stability of literary conventions and refracted those conventions through the exchange, selection, and seriality that defined newspaper networks. The term “fugitive” shifted from referring to poems published to mark one specific occasion in time to those that demonstrate the serial, circulatory, and recursive temporality of newspaper publication and readership. Fugitive poems are fluid, adaptable for new contexts and audiences. They blend the literary with the informational, as the poems’ texts and authorship narratives interweave to appeal to readers. Like other species of newspaper texts, fugitive verses were preserved through circulation, and through dynamic interplays among the networks of writers, editors, and readers who composed, recomposed, excerpted, and remediated them in both newspapers and closely related media, such as scrapbooks.

2016

1. AmP

   What Has the Digital Meant to American Periodicals Scholarship?

   Cordell, Ryan

   American Periodicals: A Journal of History & Criticism Mar 2016

   HTML
2. A Larger View of Digital American Studies

   Cordell, Ryan

   Amerikastudien/American Studies Mar 2016
3. Special Collections for All: Open, Digital Archives to Public Writing in the Literature Classroom

   Cordell, Ryan C.

   Jul 2016
4. DDH

   How Not to Teach Digital Humanities

   Cordell, Ryan C.

   Jul 2016

   Abs HTML

   Start reading this text on Debates in the DH Manifold.

2015

1. ALH

   Reprinting, Circulation, and the Network Author in Antebellum Newspapers

   Cordell, Ryan

   American Literary History Aug 2015

   HTML
2. Viral Textuality in Nineteenth-Century U.S. Newspaper Exchanges

   Cordell, Ryan C.

   May 2015
3. ALH

   Computational Methods for Uncovering Reprinted Texts in Antebellum Newspapers

   Smith, David A.,  Cordell, Ryan,  and Mullen, Abby

   American Literary History May 2015

   HTML

2014

1. IEEE

   Detecting and Modeling Local Text Reuse

   Smith, David A., Cordel, Ryan,  Dillon, Elizabeth Maddock and 2 more authors

   In IEEE/ACM Joint Conference on Digital Libraries Sep 2014

   Abs HTML

   Texts propagate through many social networks and provide evidence for their structure. We describe and evaluate efficient algorithms for detecting clusters of reused passages embedded within longer documents in large collections. We apply these techniques to two case studies: analyzing the culture of free reprinting in the nineteenth-century United States and the development of bills into legislation in the U.S. Congress. Using these divergent case studies, we evaluate both the efficiency of the approximate local text reuse detection methods and the accuracy of the results. These techniques allow us to explore how ideas spread, which ideas spread, and which subgroups shared ideas.

2. ACL

   Detecting and Evaluating Local Text Reuse in Social Networks

   Xu, Shaobin, Smith, David,  Mullen, Abigail and 1 more author

   In Proceedings of the Joint Workshop on Social Dynamics and Personal Attributes in Social Media Jun 2014

   HTML

2013

1. DHQ

   "Taken Possession of": The Reprinting and Reauthorship of Hawthorne’s "Celestial Railroad" in the Antebellum Religious Press

   Cordell, Ryan

   Jun 2013

   HTML
2. "This Flattering Millennium Theory": Denominationalism against Millennialism in James Fenimore Cooper’s The Crater

   Cordell, Ryan

   Jun 2013
3. IEEE

   Infectious Texts: Modeling Text Reuse in Nineteenth-Century Newspapers

   Smith, David A.,  Cordell, Ryan,  and Dillon, Elizabeth Maddock

   In 2013 IEEE International Conference on Big Data Oct 2013

   Abs HTML

   Texts propagate through many social networks and provide evidence for their structure. We present efficient algorithms for detecting clusters of reused passages embedded within longer documents in large collections. We apply these techniques to analyzing the culture of reprinting in the United States before the Civil War. Without substantial copyright enforcement, stories, poems, news, and anecdotes circulated freely among newspapers, magazines, and books. From a collection of OCR’d newspapers, we extract a new corpus of reprinted texts, explore the geographic spread and network connections of different publications, and analyze the time dynamics of different genres.

2008

1. SAF

   "Enslaving You, Body and Soul": The Uses of Temperance in Uncle Tom’s Cabin and "Anti-Tom" Fiction

   Cordell, Ryan C.

   Studies in American Fiction Oct 2008