'The Digitization of Newspaper Archives: Opportunities and Challenges for Historians'

Bingham, Adrian

doi:10.1093/tcbh/hwq007

Cited by 87 publications

(43 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…P3 reports on studies of introductions of new words into the vocabulary E8. Three of the interviewees (P1, P3, P4 ) mentioned that low OCR quality is a serious obstacle, an issue that is also reflected extensively in the literature [3,6,14]. For some research tasks, the interviewees reported to have come up with workarounds.…”

Section: Interviews: Usage Of Digital Archives By Historiansmentioning

confidence: 92%

Impact Analysis of OCR Quality on Research Tasks in Digital Archives

Traub

Ossenbruggen

Hardman

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Humanities scholars increasingly rely on digital archives for their research instead of time-consuming visits to physical archives. This shift in research method has the hidden cost of working with digitally processed historical documents: how much trust can a scholar place in noisy representations of source texts? In a series of interviews with historians about their use of digital archives, we found that scholars are aware that optical character recognition (OCR) errors may bias their results. They were, however, unable to quantify this bias or to indicate what information they would need to estimate it. This, however, would be important to assess whether the results are publishable. Based on the interviews and a literature study, we provide a classification of scholarly research tasks that gives account of their susceptibility to specific OCRinduced biases and the data required for uncertainty estimations. We conducted a use case study on a national newspaper archive with example research tasks. From this we learned what data is typically available in digital archives and how it could be used to reduce and/or assess the uncertainty in result sets. We conclude that the current knowledge situation on the users' side as well as on the tool makers' and data providers' side is insufficient and needs to be improved.

show abstract

Section: Interviews: Usage Of Digital Archives By Historiansmentioning

confidence: 92%

Impact Analysis of OCR Quality on Research Tasks in Digital Archives

Traub

Ossenbruggen

Hardman

2015

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Keyword searches also help researchers assess quickly a particular newspaper, situate content and make comparisons. 28 Researchers, including historians, recognize archives as more than collections of texts and material remains of the past. When examined closely, archives reflect assumptions about what matters most to historians, and gaps exist of what might appear unrecognizable in a particular time.…”

Section: Ethnic Newspapers and Archiving Practicesmentioning

confidence: 99%

Ethnic newspaper producers face archiving challenges

Gustafson

2015

Newspaper Research Journal

View full text Add to dashboard Cite

In-depth interviews with 19 news producers at 22 ethnic newspapers in three Pacific Northwest states reveal barriers to physical and digital preservation of back issues that include inadequate physical and digital space, limited personnel and financial resources and a lack of technological know-how for archiving the newspapers.T he day Cary Rosenbaum learned he was hired at the Tribal Tribune, a fire burned the administration building of the Confederated Tribes of the Colville Reservation to the ground. On July 29, 2013, the newspaper office in that building lost almost everything from computers to cameras to old newspapers. 1 In the days and weeks that followed, the newly hired media services manager saw the newspaper archives up close and realized the fire's toll. Just a few years earlier, when he worked in an interim position setting up the newspaper's website, he "just figured everything was taken care of" 2 in terms of archiving the Nespelem, Washington, newspaper, which had published since 1960. 3 It was not until Rosenbaum was hired and in charge that he realized the scope of a fire that had burned a recent decade of newspapers, and he also recognized how rodents and rain could harm even older records that were stored in buildings nearby. "We kind of had a fire lit under us, so-to-speak, when they told us we needed to remodel the community center where one-half of [the newspapers were] put," 4 Rosenbaum said. His work as a sports writer for the daily Coeur d'Alene Press andGustafson is a lecturer in the School for Interdisciplinary Arts

show abstract

“…There have been inspiring examples of good digital historical scholarship, like the use of N-grams to mine the Google Books archive (Michel, 2010), the engagement in creative visual analysis of historical geography, 1 or the study of the 'circulation of knowledge and learned practices' by means of a virtual research environment (VRE). 2 However, historians are still in the process of learning how to incorporate and implement data-mining technology in methodologically sound and reproducible ways (Seefeldt and Thomas, 2009;Bingham, 2010;Earheart and Jewell, 2011;Berry, 2012;Burdick et al, 2012;Van Eijnatten et al, 2013;Van Eijnatten et al, 2014). 3 Semantic text analytics is a particularly promising form of text mining that can be applied to 'big data' sets.…”

Section: Introductionmentioning

confidence: 99%

A Digital Humanities Approach to the History of Culture and Science: Drugs and Eugenics Revisited in Early 20th-Century Dutch Newspapers, Using Semantic Text Mining

Snelders¹,

Huijnen²,

Verheul³

et al. 2017

CLARIN in the Low Countries

View full text Add to dashboard Cite

Human language technology developed and used in CLARIN demonstrator projects WAHSP and BILAND supports advanced forms of (multi-lingual) text mining of large datasets of newspapers. We argue that the combination of exploratory search and text mining o ers an innovative research approach to systematically set up search trails in the historical sciences. We describe the development, use, and methodological challenges of the WAHSP and BILAND text-mining tools and the successor tool, Texcavator, to support alternating forms of distant reading and close reading in newspaper collections. We will show how semantic text mining speeds up the heuristic process and thus helped to provide new and challenging perspectives on the circulation of ideas and notions regarding drugs and eugenics in Dutch newspapers in the rst four decades of the 20th century. IntroductionHistorical scholars are increasingly applying computational tools and methods to all phases of their research. Digital tools are used to open, present, and curate textual and multi-media sources in semantic text mining, for integration of geospatial information data, for various forms of visualisation, and for enhanced and multi-media publication of research results, blogs, and wikis. Digital history is a methodological approach that is framed by these digital tools' ability to make, de ne,

show abstract

'The Digitization of Newspaper Archives: Opportunities and Challenges for Historians'

Cited by 87 publications

References 0 publications

Impact Analysis of OCR Quality on Research Tasks in Digital Archives

Impact Analysis of OCR Quality on Research Tasks in Digital Archives

Ethnic newspaper producers face archiving challenges

A Digital Humanities Approach to the History of Culture and Science: Drugs and Eugenics Revisited in Early 20th-Century Dutch Newspapers, Using Semantic Text Mining

Contact Info

Product

Resources

About