Articles from Digital Scholarship in the Humanities (formerly LLC)

Representing stories as interdependent dynamics of character activities and plots: A two-mode network relational event model

AbstractRecent advances in data science and machine learning have enhanced our ability to analyze and understand the structure of social interactions in fictional stories by using formal and quantitative approaches. However, an objective assessment of these aspects of fictional stories remains a relatively new and technically difficult field. In this brief report, we introduce our study in which we modeled story dynamics from a novel perspective.

Machine learning, template matching, and the International Tracing Service digital archive: Automating the retrieval of death certificate reference cards from 40 million document scans

AbstractScattered throughout the International Tracing Service (ITS) digital archive, one of the largest and most heterogeneous collections of Holocaust-related material, are hundreds of thousands of reference cards to official death certificates recording a fraction of individuals who perished within concentration camps. These cards represent the most comprehensive collection of digital material pertaining to these death certificates issued by Sonderstandesamt Arolsen, a German civil registry office.

Digital, digitized, and numerical humanities

AbstractThe term ‘digital humanities’ may be understood in three different ways: as ‘digitized humanities’, by dealing essentially with the constitution, management, and processing of digitized archives; as ‘numerical humanities’, by putting the emphasis on mathematical abstraction and the development of numerical and formal models; and as ‘humanities of the digital’, by focusing on the study of computer-mediated interactions and online communities.

Evaluation software for effects produced by MOOC in mediums with different linguistically levels

AbstractMOOC appearance has produced, in a first phase, more discussions than contributions. Despite pessimistic opinions or those catastrophic foreseeing the end of the classic education by accepting MOOC, the authors consider that, as it is happening in all situations when a field is reformed, instead of criticism or catastrophic predictions, an assessment should be simply made. MOOC will not be better or worse if it is discussed and dissected but can be tested in action, perfected by results, or abandoned if it has no prospects. Without testing, no decision is valid.

A ‘wind of change’—shaping public opinion of the Arab Spring using metaphors

AbstractNewspapers create publicity, draw attention to topics, and try to gain thematic acceptance from the reader. To achieve this, they use linguistic strategies and select culturally and historically evolved encyclopedic knowledge sources. In our pilot study we explore the presentation of the events in the Middle East–North African region between December 2010 and November 2011 that were soon metaphorically framed as the Arab Spring. To this end, we use a text corpus consisting of 300 opinion pieces from five national German newspapers.

A sentiment analysis system for social media using machine learning techniques: Social enablement

AbstractIn this article, an innovative approach to perform the sentiment analysis (SA) has been presented. The proposed system handles the issues of Romanized or abbreviated text and spelling variations in the text to perform the sentiment analysis. The training data set of 3,000 movie reviews and tweets has been manually labeled by native speakers of Hindi in three classes, i.e. positive, negative, and neutral. The system uses WEKA (Waikato Environment for Knowledge Analysis) tool to convert these string data into numerical matrices and applies three machine learning techniques, i.e.

In defense of sandcastles: Research thinking through visualization in digital humanities

AbstractAlthough recent research acknowledges the potential of visualization methods in digital humanities (DH), the predominant terminology used to describe visualizations (prototypes and tools) focuses on their use as a means to an end and, more importantly, as an instrument in the service of humanities research. We introduce the sandcastle as a metaphorical lens and provocative term to highlight visualization as a research process in its own right.

Attributing the Bixby Letter using n-gram tracing

AbstractThere is a long-standing debate about the authorship of the Bixby Letter, one of the most famous pieces of correspondence in American history. Despite being signed by President Abraham Lincoln, some historians have claimed that its true author was John Hay, Lincoln’s personal secretary. Analyses of the letter have been inconclusive in part because the text totals only 139 words and is thus far too short to be attributed using standard methods.

Johnson, ‘Misargyrus’, and Richard Bathurst

AbstractFour letters in the Adventurer are currently attributed to Johnson, who allegedly disguised his style so that they could be plausibly ascribed to his friend Richard Bathurst. A stylometric analysis, supported by internal evidence, finds the case for disguise implausible, and suggests that the letters are a collaboration between Johnson and Bathurst.