[en] Unveiling the Editing Process of Japanese Demons Picture Scrolls:
How Digital Humanities Played a Role in Developing a New Theory in Art HistoryShoji Yamada, International Research Center for Japanese Studies
Abstract
[en]
This paper examined seventy-one “Hyakki Yagyō Emaki”
(“Night Parade of One Hundred Demons” Picture Scroll; Demons Scroll) and estimated the artistic editing
process using a digital humanities approach. The edit distance was used to illustrate the lineage trees
of Demons Scrolls, focusing on the arrangement of the demons in the procession. The author concluded that
a type of scroll depicted the demon arrangement closest to the prototype of the renowned Shinjuan lineage
scrolls. By numbering the demons in the procession, the author contributed quantitative evidence to the
ongoing iconographical interpretation debate. The paper ends with a discussion of new questions
regarding Demons Scrolls that have arisen as a result of this research. By applying similar methods to other
materials, the scope of digital humanities can be expanded.
[en] What Counts? Digital Humanities Pedagogy Seminars as TeachingCrystal Hall, Bowdoin College; Lauren Tilton, University of Richmond; Griffin Ng, Bowdoin College
Abstract
[en]
Digital Humanities pedagogy seminars (DHPSs) are a common occurrence on small liberal arts campuses that are seen as acts of
service within the logic of the Teaching-Research-Service model of tenure and promotion in the U.S. academy. Yet, the goal of
these events is to teach faculty colleagues DH methods, inflected by DH pedagogy values, which they can then use in their
undergraduate courses. As tenured and tenure-track DH specialists at small liberal arts colleges, we argue that a DHPS is
pedagogical labor and should be evaluated as teaching in order to enact values-based DH more broadly. The paper provides
qualitative data based on experiences at our institutions as well as quantitative data about 226 DHPSs offered in North
America from July 2015 to July 2019. We focus on the impact of DHPS duration and the home institutions and roles of instructors
on collaboration, experimentation, and intersectional feminism as practiced in the field.
[en] AR and Public Participation in Maputo City: An
Exploratory StudyAnselmo Matusse, Bloco 4 Foundation, Maputo, Mozambique
Abstract
[en]
This study examines the potential of using Augmented Reality to increase urban
participation to deal with identified problems in Maputo city, Mozambique, southern
Africa. The study’s aim is twofold; first, it seeks to add to the nascent literature
on Augmented Reality (AR) in Africa; second, to experiment with AR for public
participation in urban Maputo to explore the affordances of AR and examine the
possibility and limitations of deploying the technology for such purposes. The study
concludes that AR can enhance public participation and engagement with public spaces
in Maputo city. However, technical and economic limitations must be considered when
designing projects to deploy AR technologies in the city.
[en] Problems of Authorship Classification: Recognising the Author Style or a Book?František Válek, National Library of the Czech Republic; Department of Philosophy and Religious Studies, University of Pardubice; Institute of Ancient Near Eastern Studies, Charles University; Jan Hajič, Jr., National Library of the Czech Republic; Masaryk Institute and Archive, Czech Academy of Sciences; Institute of Formal and Applied Linguistics, Charles University
Abstract
[en]
The presented article proposes that one of the problems regarding authorship attribution tasks is the attribution of a
specific book rather than the author. This often leads to overestimated reported performance. This problem is in general
connected to the dataset construction and more specifically to the train-test data split. Using a heavily delexicalized
and diverse dataset of Czech authors and basic LinearSVC classifiers, we designed a three-step experiment setting to
explore book versus author attribution effects. First, the authorship attribution task is performed on a dataset split
to train and test data segments across books. Second, the same task is performed on a dataset where individual books
are used wholly either for training or testing. Expectedly, this leads to poorer results. In the third step, we do not
attribute book segments to authors but to books themselves. This step reveals that there is a general tendency towards
attributing to a specific book rather than to different books of the same author. The results indicate that authors
who show a higher inner confusion among their works (i.e., the model attributes their works to other works of theirs)
tend to perform better in the task of attribution of an unseen book.
[en] Seeking Information
in Spanish Historical Newspapers: The Case of Diario de
Madrid (18th and 19th Centuries)Eva Sánchez-Salido, ETSI Informática, UNED; Antonio Menta, ETSI Informática, UNED; Ana García-Serrano, ETSI Informática, UNED
Abstract
[en]
New technologies for seeking information are based in machine learning techniques
such as statistical or deep learning approaches that require a large number of
computational resources as well as the availability of huge corpora to develop the
applications that, in this concrete sub-area of Artificial Intelligence, are the
so-called models. Nowadays, the reusability of the developed models is
approached with fine-tuning and transfer learning techniques. When the available
corpus is written in a language or domain with scarce resources, the accuracy of
these approaches decreases, so it is important to address the start of the task by
using state-of-the-art techniques.
This is the main problem tackled in the work presented here, coming from the art
historians’ interest in an image-based digitized collection of newspapers called
Diario de Madrid (DM) from the Spanish press between
18th and 19th centuries, which is freely available at the Spanish National Library
(BNE). Their focus is on information related to entities such as historical persons,
locations as well as objects for sale or lost and others, to obtain geo-localization
visualizations and solve some historical riddles. The first step needed technically
is to obtain the transcriptions of the original digitalized newspapers from the DM
(1788-1825) collection. After that, the second step is the development of a Named
Entity Recognition (NER) model to label or annotate automatically the available
corpus with the entities of interest for their research. For this, once the CLARA-DM
corpus is created, a sub-corpus must be manually annotated for the training step in
current Natural Language Processing (NLP) techniques, using human effort helped by
selected computational tools. To develop the necessary annotation model (CLARA-AM),
an experimentation step is carried out with state-of-the-art Deep Learning (DL)
models and an already available corpus, which complements the corpus that we have
developed.
A main contribution of the paper is the methodology developed to tackle similar
problems like that of art historians’ digitized corpus: selecting specific tools when
available, reusing developed DL models to carry out new experiments in an available
corpus, reproducing experiments in the art historians’ own corpus and applying
transfer learning techniques within a domain with few resources. Four different
resources developed are described: the transcribed corpus, the DL-based transcription
model, the annotated corpus and the DL models developed for the annotation using a
specific domain-based set of labels in a small corpus. The CLARA-TM transcription
model learned for the DM is accessible from January 2023 at the READ-COOP website
under the title “Spanish print XVIII-XIX - Free Public AI Model
for Text Recognition with Transkribus”(https://readcoop.eu/model/spanish-print-xviii-xix/).
[en] A Review of Oral Tradition
and the Internet: Pathways of the Mind by John Miles FoleyAli M. Rahman, UC Santa Barbara
Abstract
[en]
Described by the author as a “morphing book”, John Miles
Foley’s Oral Tradition and the Internet: Pathways of the
Mind is an ambitious project that extends from the textual to the
digital. Through a nonlinear reading, the book illustrates and explains to
readers the various similarities and potential interactions “between humankind’s oldest and newest thought technologies.” Without
traditional organization, the book invites readers to jump from section to
section much like the way one might peruse a website — and in fact was paired
with the accompanying Pathways Project website (currently offline). The nodes as
Foley calls them (small chapters arranged in alphabetical order) cover a variety
of topics, utilizing the authors prefix appended terminology (such as tAgora and
ewords) including thought experiments that challenge our conception of what
constitutes a text. The argument lies therein: a nontraditional and nonlinear
“book” reveals the tension and dynamic relationship
between oral tradition and Internet technology.
[en] Rich Veins of Ore: A Review of Gabe Ignatow and Rada
Mihalcea’s An Introduction to Text Mining: Research Design, Data
Collection, and AnalysisCharlie Harper, Case Western Reserve University
Abstract
[en]
An Introduction to Text Mining: Research Design, Data
Collection, and Analysis by Gabe Ignatow and Rada Mihalcea is most
effective in balancing clear explanations of analytical techniques with sufficient
technical details to engage a cross-disciplinary audience. Its process-oriented
approach can broaden interest and build greater proficiency in applied
text-mining.
[en] A Synoptic Primer: Review of Wissensrohstoff Text: Eine Einführung in das Text Mining (2022)Michael Richter, University of Leipzig
Abstract
[en]
Biemann, Heyer, and Quasthoff’s Wissensrohstoff Text is concerned with conveying a basic understanding of the models and techniques of text mining, as well as insight into which method is procedurally suitable for whichever problem in this area. The book imparts indispensable knowledge, and the new edition makes it possible to describe and discuss the most recent developments in text mining. The book deals also with linguistic fundamentals and with principles of human language processing which is very noteworthy and a unique asset. The book shows in an exemplary way how complex knowledge can be conveyed by means of didactic reduction.
