Quantitative Analysis of Canon vs. Non-Canon in Persian Novels: A Computational Study of 650 Works
Sedaghat Payam, Mehdy
University of Maryland, United States of America
This computational study of 650 Persian novels focuses on the distinction between canonical and non-canonical works, using advanced digital humanities techniques like topic modeling and stylometric analysis. It hypothesizes that canonical novels, known for enduring quality, display distinct thematic and stylistic elements. Findings indicate that canonical works address complex societal issues with stylistic sophistication, while non-canonical texts focus on personal narratives.
Data Modeling for Historical Manuscripts: Relational Database Design for an Ottoman Fiscal Codex
ÖNCEL, FATMA (1,2); YAYCİOGLU, ALİ (2); ÇOLAKOĞLU, EZGİ (3)
1: Bahçeşehir University, Turkey; 2: Stanford University, USA; 3: University of Bologna, Italy
HTML XMLThis poster presents the construction of a relational database for an Ottoman fiscal codex dated 1808-20. It offers a walkthrough of the steps involved in creating the database within an RDBMS framework, presents a user scenario for analyzing the role of inventory management and debt settlement in Ottoman power making.
ARORA: Digital Monuments for a More Inclusive World
Wichmann, Anne (1,2); Francesca, Clara (1,2)
1: ARORA, United States of America; 2: Extended Reality Ensemble (XRE), United States of America
HTML XMLWe present ARORA. a project aimed at reshaping public landscapes through the integration of gender-diverse Augmented Reality (AR) and sound monuments. The initiative seeks to redress the current imbalance in public monuments, where in nearly all cities more than 90% depict male figures, predominantly white, often glorifying war.
Annotating Spatiality in Literary Texts: The Category Set CANSpiN.CS1
Lemke, Marc; Kellner, Nils; Henny-Krahmer, Ulrike
University of Rostock, Germany
With our submission we present the annotation guideline CANSpiN.CS1 of the project "Computational Approaches to Narrative Space in 19th and 20th Century Novels" (CANSpiN). It is intended to demonstrate the project’s first step in developing computer-aided methods for recognizing and analyzing narrative space in literary texts with machine-learning methods.
An Analysis of Linguistic Turn of Archive in Digital Humanities Research
LONG, Jiaqing (1,2); FENG, Huiling (1,2)
1: Renmin University of China, China, People's Republic of; 2: Center for Digital Humanities at Renmin University of China
This study mainly reveals the phenomenon of the linguistic turn of “archive” in digital humanities research. The paper selected 51 award-winning cases of the International Digital Humanities Award (DHA) from 2012 to 2022 as samples, conducted structured coding analysis on them, and obtained three linguistic turn characteristics.
Authorial Mimicry by Large Language Models: A First Assessment
Giovannini, Luca (1,2); Skorinkin, Daniil (1)
1: Universität Potsdam, Germany; 2: Università di Padova, Italy
HTML XMLThis contribution explores how large language models attempt to replicate the authorial voices of some canonical authors. To achieve this, corpora of human- and AI-generated short stories are compared through several methods from computational literary studies to assess differences in terms of content and style.
The DH Landscape in China
XIAO, SHUANG; MURPHY, ORLA
University College Cork, Ireland
HTML XMLThis poster will utilise a variety of visualisation methods to comprehensively present the development of Digital Humanities in China, both temporally and spatially. It will include detailed information on academic achievements, infrastructure, research centres, research projects, disciplinary education, and academic journals.
Implementing interpretable models in stylometric analysis
Ochab, Jeremi K. (1,2); Walkowiak, Tomasz (2)
1: Jagiellonian University, Kraków, Poland; 2: Faculty of Information and Communication Technology, Wroclaw University of Science and Technology, Wroclaw, Poland
HTML XMLWe present a modular software pipeline for interpretable stylometric analysis. It connects modern text preprocessing and extraction of linguistic features with various NLP tools, a state-of-the-art classifier, an explainability module, and finally visualisation that shows general and detailed explanations of what linguistic features make text collections or individual texts differ.
Time Horizons of Speculative Fiction
Wythoff, Grant
Princeton University, United States of America
Time Horizons of Speculative Fiction is a dataset that collects 2,400 works of English-language speculative fiction set in the future, each marked with the year it was published and the year it takes place. Allows for analyses of how far a future the genre has imagined from 1733 - 2023.
Penfield African American Cemetery Restoration Project
Roberts, Spencer William
Emory University, United States of America
This project is a large-scale, multi-organization collaboration to clean up, document, and restore the Penfield African American Cemetery, a historic antebellum burial ground that has been made inaccessible for over seventy years. Work includes: (1) clearing debris and restoring markers; (2) mapping grave sites with ground-penetrating radar; and (3) archiving geophysical data to support community-driven goals for research and commemoration.
Research on the Multidimensional Feature Analysis Model of Local Gazetteers from the Perspective of Cultural Computing
Niu, Li; Li, Anrunze; Jin, Chi
RENMIN UNIVERSITY of CHINA, China, People's Republic of
HTML XMLComparing the huge potential value of local gazetteers with the current situation of insufficient excavation, we conduct an overall framework of cultural computation methodology, which locks the development objects of local gazetteers into five categories of carrier features, thematic features, elemental features, associated features and numerical features.
Coding DH Project: Exploring DH Coding Communities and Practices on GitHub
LeBlanc, Zoe (1); Wieringa, Jeri (2)
1: University of Illinois Urbana-Champaign; 2: Princeton University
Within the Digital Humanities, GitHub has become the platform for code work. Yet how DH scholars use GitHub and the impact of these practices on research and teaching remains underexplored. This poster presents ongoing research exploring practices captured within GitHub, highlighting results from our data collection via the GitHub API.
Multi-viewpoint ontologies as a new paradigm for investigating minorities’ cultural heritage: The case of the global Jewish minority
Zhitomirsky-Geffet, Maayan (1); Kizhner, Inna (2)
1: Bar Ilan University, Israel; 2: Haifa University, Israel
HTML XMLCultural heritage of ethnic minorities is diverse and multi-vocal in essence. In this study, we introduce a new paradigm for investigating minorities’ heritage as presented in online museum collections around the globe based on a multi-viewpoint ontology that conveys a diversity of external and internal views of the minority cultures.
Towards an analysis of perception biases in historical networks: Synergies between Social Sciences and Digital Humanities
Dörpinghaus, Jens (1,2); Helmrich, Robert (1); Tiemann, Michael (1)
1: Federal Institute for Vocational Education and Training (BIBB), Germany; 2: University of Koblenz, Germany
The intersection of digital humanities and computational social sciences can be used to deepen our understanding of complex socio-cultural phenomena. This poster presents an approach to studying perceptual biases in historical networks, how these methods can be applied, and the methodological challenges that arise.
Catch Our DHRIFT: DH Workshops for Responsible Reuse
Zweibel, Stephen; Rhody, Lisa Marie; Lloyd, Zachary; Fan, Leanne
Graduate Center, CUNY, United States of America
DHRIFT is an open educational resource and workshop publishing platform for teaching and learning technical skills. Showcasing DHRIFT’s directory of interactive DH workshops, this poster and demonstration will cover learning with DHRIFT, reproducing, customizing, and developing your own DHRIFT publication, and develop new workshops with the DHRIFT platform.
MEMORISE: An Infrastructure to Preserve Memories on Nazi Persecution
Jänicke, Stefan (1); Khulusi, Richard (2); Ebbrecht-Hartmann, Tobias (3)
1: University of Southern Denmark, Denmark; 2: Bergen-Belsen Memorial, Germany; 3: The Hebrew University of Jerusalem, Israel
MEMORISE was funded in times of the COVID-19 pandemic, which showed the need to develop novel digital solutions to preserve and make cultural heritage accessible. We will discuss the suitability, added value, and effectiveness of digital solutions to educate on Nazi crimes and to make memories virtually accessible.
SILICON: Supporting Digitally-Disadvantaged Languages
Dombrowski, Quinn; McDivitt, Anne Ladyem; Mullaney, Thomas; Starkey, Kathryn; Treharne, Elaine
Stanford University, United States of America
HTML XMLStanford University’s SILICON project was created at the intersection of multilingual DH, design, and human-computer interaction, with the goal of pushing forward the usability of new scripts once they have passed the encoding stage in order to help digitally-disadvantaged languages thrive.
Reinvention as DH Praxis: Reflecting on (Nearly) a Decade of the Global DH Symposium
Mapes, Kristen (1); Topham, Kate (1); Jacob, Arun (2)
1: Michigan State University, United States of America; 2: University of Toronto, Canada
The Global DH Symposium foregrounds voices from the Global South and marginalized communities. This poster focuses on three areas of reinvention driven by our values and speaks to the ways that we hold ourselves responsible to the community we have cultivated: (1) open peer review; (2) modality; (3) publication venues.
The ModelSEN Framework: Current Insights and Future Directions
Schlattmann, Raphael (1,2,3); Kaye, Aleksandra (1,2); Vogl, Malte (1); Schmitz, Jakob Merijn (2,4); Weiß, Lea (2,3); von Welczeck, Laura (2,5)
1: Max Planck Institute of Geoanthropology, Germany; 2: Max Planck Institute for the History of Science, Germany; 3: Technical University of Berlin, Germany; 4: The Humboldt University of Berlin, Germany; 5: Free University of Berlin, Germany
HTML XMLThe poster will explain the theoretical assumptions and the main idea behind Socio-epistemic Networks, a framework intended to explore the dynamics that govern the formation and evolution of knowledge systems, combining approaches of network analysis and computer linguistics with questions about knowledge formalisation, dissemination and acquisition.
The Quantitative Dimension of Ancient Chinese Literature Research and The Digitization of Canons
Song, Runze
Shanghai University, China, People's Republic of
HTML XMLThe digitization of canons has facilitated the emergence of novel methodologies in the field of ancient Chinese literature. Quantitative research relying on digital tools have gradually become an integral part of scholarly discourse through the retrieval and analysis of extensive corpora, which have engendered contemplation and conceptual reinvention among scholars.
AI Models and Services for the Leopardi Digital Library
Santini, Cristian; Marozzi, Gioele; Frontoni, Emanuele; Melosi, Laura
University of Macerata, Italy
HTML XMLThis paper explores the integration of Artificial Intelligence techniques into the Leopardi Digital Library, aiming to enhance the accessibility of Giacomo Leopardi's literary works. The proposed AI-based architecture offers a user-friendly interface, emphasizing responsible implementation and addressing challenges for effective utilization of AI technologies in cultural heritage preservation.
Modeling Social History: A Deep Learning Approach to Arabic Historical Tradition
Gonzalez Martinez, Alicia (1); Reza Hakimi, Hamid (1); Mischer, Lisa (1); Romanov, Maxim (1); Yousef, Tariq (2)
1: University of Hamburg; 2: University of Southern Denmark, Denmark
The poster presents interim results of an ongoing project that pursues the modeling of the social history of the premodern Islamicate world from the rich historical and biographical texts, which are characteristic of the Arabic written tradition. Leveraging advancements in language modeling and deep learning.
Digital Humanities for pupils. First results of creating a learning lab.
Muenster, Dora Luise; Muenster, Sander
FSU Jena, Germany
HTML XMLDigital literacy are becoming increasingly important. The aim of this contribution is to (a) examine the current state of educational programmes in the field of Digital Humanities (b) present the current state of teaching labs in the field of digital history, and (c) present first results of creating a learning lab for pupils.
Finding connections between fundamentally different conceptions of “models”: Explorations of highly structured data in the context of Large Language Models.
Bradley, John
King's College London, United Kingdom
HTML XMLExploring the complementary semantics of text embedded in highly structured data with established tools (such as those found in Voyant) and LLM Embeddings, with the data structure itself. What does the text approach add to our understanding of the "full semantics" of these projects.
Dissecting the Avvisi: Utilizing Genre-Defining Layout Characteristics for Data Collection and the Reconstruction of News Itineraries
Kreuze, Wouter Paul (1,2)
1: German Historical Institute Washington, United States of America; 2: George Mason University, United States of America
The layout of early modern manuscript newsletters consisted of several layers. Each of these layers offers another clue about the itinerary of a piece of news. By taking all layers into account in a spatial analysis, I endeavor to shed new light on the dissemination of the news.
<em>Literature in Context</em>: Reinventing the Anthology as a Digital Open Educational Resource
Howe, Tonya (1); O'Brien, John (2); Ruotolo, Chris (3)
1: George Mason Universiry, United States of America; 2: University of Virginia, United States of America; 3: University of Virginia, United States of America
Literature in Context: An Open Anthology of Literature in English, 1400-1925 is an open source OER project developed with the goals of equity and social justice in view. In a globally-shifting academic landscape, we have a responsibility to produce, use, and disseminate digital work that can reinvent access to education.
Charting the Evolution of Topics and Ideas in the Princeton Prosody Archive
Haverals, Wouter; Heuser, Ryan
Princeton University, USA
This presentation explores the evolution of poetic concepts in the Princeton Prosody Archive, comparing various topic modeling techniques such as NMF, LDA, and BERTopic. It highlights how these methods reveal latent themes in versification manuals, illuminating the interplay between poetic form, language evolution, and socio-political contexts from 1559 to 1927.
"What's Past is Prologue...": New perspectives on Shakespeare's character networks
Kristensen-McLachlan, Ross Deans (1,3); Ladegaard, Jakob (2)
1: Department of Comparative Literature, Aarhus University, Denmark; 2: Center for Humanities Computing, Aarhus University, Denmark; 3: Department of Lingusitics, Cognitive Science, and Semiotics, Aarhus University
This poster presents an overview of work found in the forthcoming book "The Arden Enyclopedia of Shakespeare's Language, Volume 4: Character Networks". This volume in the series provides the first systematic, consistent, and in-depth analysis of character networks in all of Shakespeare’s 38 plays.
Building and employing new digital resources for the study of US scientific advisors
Von Arx, Devin; Traylor, Jordan; Evans, Kenneth Mellinger
Rice University's Baker Institute for Public Policy, United States of America
This poster presents preliminary work processing, organizing, and analyzing materials in the White House Scientist and Science Policy Dynamic Digital Archive (DDA), a new online collection hosted by Rice University. In particular, the poster describes the development and study of a django-enabled relational database of DDA materials.
Overcoming OCR Inaccuracies in Historic Newspaper Directories: Improving Digital Archaeology and Digital Humanities Data Pipelines
Evans, Daniel John; Naiman, Jill P.; Downie, J. Stephen
University of Illinois, United States of America
This poster focuses on correcting OCR-generated errors in late 19th- and early 20th-century American newspaper directories and presents a pipeline that tests the accuracy of five post-correction models. It presents findings and a synthetic dataset that will guide researchers in selecting suitable models for fine-tuning OCR output for future research.
Determining a ‘Cultural Literacy Quotient’ for Latin Readability
Burns, Patrick J.
Institute for the Study of the Ancient World / New York University, United States of America
Following the work of Latinist Kenneth Kitchell Jr., I introduce a computationally derived “cultural literacy quotient,” defined here as the density of automatically tagged named entities in a given passage, as a way to assist teachers in gauging the relative difficulty of Latin texts for beginning and intermediate students.
Leveraging Bidirectional Encoder Representations from Transformers (BERT) for Analyzing Ancient Buddhist Texts
Li, Tong
The Chinese University of Hong Kong
HTML XMLThis ongoing research applies the BERT language model to analyze ancient Buddhist texts in classical Chinese for sentence segmentation and punctuation restoration. Leveraging the CBETA dataset and contextual embeddings, this research tackles the unique linguistic challenges of ancient Buddhist literature.
Visualization-Based Storytelling in Holocaust Education: The Integration of Testimonies, Art, and Technology
Kusnick, Jakob
University of Southern Denmark, Denmark
HTML XMLThis poster presents an innovative approach to visualizing the tragic narratives of Nazi persecution and the Holocaust through a multidisciplinary storytelling approach. By employing a diverse range of multimedia annotations in addition to data visualizations, offering a deeply immersive communication of individual biographies and collective experiences
Collaborative Course Design and Humanities Data Storytelling
Gudzunas, Ava; Eichmann-Kalwara, Nickoal
University of Colorado Boulder, United States of America
This presentation explores the collaborative partnership between an undergraduate student and a faculty librarian in co-designing a humanities data storytelling course. We examine power dynamics and care, as well as data pedagogy and knowledge production in the undergraduate humanities classroom.
Digital Echoes of European Heritage: Unravelling Narratives with Latin American Women's Inights
Comino, Alba
Universidade Nova de Lisboa, Portugal
The REWIND project analyses European cultural heritage through the lens of Latin American women travellers. It combines computational linguistics and geographic information systems techniques with an ontological model and sentiment analysis algorithms to break Eurocentric, patriarchal, and androcentric narratives, fostering inclusive historical discourses and sustainable tourism.
Defamiliarizing Images from the Time magazine archive: A web prototype
Jofre, Ana
SUNY Polytechnic, United States of America
We present a web-based prototype of a digital visualization tool, Faces in Time, that allows users to investigate images of faces extracted from the pages of Time magazine. Our archive of Time contains 3,389 issues ranging from 1923 to 2014, and the visualized data comprises up to 327,322 faces.
Clustering Ashkenazi Manuscripts
Vasyutinsky Shapira, Daria; Kurar Barakat, Berat; Suliman, Mohammad; Gogawale, Sharva; Dershowitz, Nachum
Tel Aviv University, Israel
We present the initial results of several different deep-learning approaches for clustering the dataset of manuscripts written in the Ashkenazi Square type-mode of medieval Hebrew script. The research combines Deep machine learning and Hebrew paleography.
Observations in Students’ Theses – A Critical Analysis of Use-Cases, Models and Problems in Natural Language Processing
Jegan, Robin
University of Bamberg, Germany
HTML XMLThis poster will present observations gathered across several bachelor’s and master’s theses that were supervised at a German university. Conclusions regarding modern neural networks when compared to simpler and more traditional models will be presented as well as common problems across several theses.
A Bibliometric Analysis of Research Trends in Digital Humanities
Jeong, Yoo Kyung (1); Kim, Erin Hea-Jin (2)
1: Hannam University, Korea, Republic of (South Korea); 2: Kongju National University, Korea, Republic of (South Korea)
HTML XMLIn this study, we aim to explore the interdisciplinarity and diversity of research areas in digital humanities, focusing on key researches that have influenced the field’s development by utilizing bibliometric analysis and network analysis.
ontoNLP: A Mechanism for Transforming Textual Data into Structured Data
Wang, Jun (1,2); Wei, Tong (1,2); Tang, Xuemei (1,2); Wang, Zhaoji (1,2)
1: The Department of Information Management, Peking University, China; 2: The Research Center of Digital Humanities, Peking University, China
PDFThis article delves into the intersection of ontology and natural language processing (NLP) technology within the realm of annotation. It proposes an ontoNLP mechanism for automated annotation based on pre-defined ontology, aiming to facilitate the transformation of textual data into structured datasets.
Sonic Landscapes in the Digital Realm: An Examination of Music Performance and Diversity, Equity and Inclusion through Digital Humanities
Lai, Katie (1); Chan, Holly (2)
1: McGill University; 2: The Hong Kong University of Science and Technology
HTML XMLUsing open data, this research examined McGill University’s EDI endeavor in concert programming through data mining and digital humanities methodologies. The findings reveal the level of inclusion of underrepresented composers and repertoire diversity in the past decades. It further provides insights that help foster a diverse and inclusive music environment.
What Wikibase can offer in its own right? The Timna Valley database case study
Silber-Varod, Vered; Gichon, Eshchar; Klein, Stav; Evenstein Sigalov, Shani; Ben-Yosef, Erez
Tel Aviv University, Israel
HTML XMLTimna Valley is one of the oldest and best-preserved ancient copper mining areas in the world. The extensive data collected include thousands of digital files of varied types. Our goal is to make these data available to other scholars as well as the wide public, principally using Wikibase.
Knowledge Discovery of Traditional Chinese Medicine Ancient Books in the Perspective of Digital Humanities--Taking the Use of traditional Chinese Medicine Baizhu in the <em>Treatise on Febrile and Miscellaneous Diseases</em> as an Example
Wang, Yu; Yan, Han; Wang, Binxuan
School of Information Management, Wuhan University, China, People's Republic of
This paper discusses the use of the Chinese herb Baizhu in Treatise on Febrile and Miscellaneous Diseases. Frequency analysis method and association rule mining method were adopted. We find that Baizhu is widely used to treat spleen deficiency, cough, diarrhea and vomiting. Baizhu often in conjunction with Gancao/Fuling/Guizhi/Ganjiang et al.
The Impact of ICT Use on the Cultural Capital Acquisition of College Students form Rural Areas
Liao, Jingpei (1); Liu, Chang (1,2)
1: Renmin University of China, China; 2: Vrije Universiteit Brussel, Belgium
HTML XMLThis study mainly applies the grounded theory to explore the impact of ICT usage behavior on the cultural capital acquisition of college students from rural areas of Liangshan, Sichuan Province, China. Based on this, the study provides reference for public cultural services and digital construction of cultural resources.
New Generation of Electronic Edition for Neo-Latin Literature – Rescue from Oblivion, Stage Two
Urban-Godziek, Grażyna; Grabska-Gardzińska, Iwona
Jagiellonian University in Krakow, Poland
HTML XMLA new version of NEOLATINA, a repository of critical editions of Latin texts created by Old-Polish authors. We transfer data from an old (2006) database to the new, based on TEI Publisher, which enables comparing language versions, searching for similarities for linguistic commentary and comparing original, translation and facsimile.
A Semi Automated Approach to Identification and Mitigation of Narrative and Memory Biases in Textual Data
Joseph, Justy (1); Menon, Nirmala (2)
1: Indian Institute of Technology, India; 2: Indian Institute of Technology, India
This paper traces the history of bias analysis by outlining its major approaches. Based on the comparative analysis of four exquisite media bias detecting metrics, the study proposes a semi-automated target-oriented memory and narrative bias detection and classification tool for texts of 1947 partition at different levels of granularity.
Should Linked Open Data be only an option for digital humanities projects? Notes from IHC’s Digital Humanities Lab and ROSSIO Infrastructure
Alves, Daniel; Paulino, Joana Vieira
Institute of Contemporary History, NOVA FCSH / IN2PAST, Portugal
The aim of the paper is to present and reflect about the DH_Lab's (NOVA FCSH) and ROSSIO Infrastructure's experience regarding the application of LOD and web semantic’s principles, focusing on tested solutions related to the availability, connection, contextualization, and reusability of digital data from research projects and GLAM institutions.
Tracing Emotions in Pardon Tales: Sentiment Analysis of Legal Narratives from 16th Century Western Europe
Sun, Heling; Mo, Ru; Zhang, Guangwei
Shaanxi Normal University, China, People's Republic of
This article explores the role of sentiment and emotion in shaping pardon tales from 16th-century Western Europe, using sentiment analysis (SA) techniques grounded in digital humanities. By applying SA, we aim to dynamically model emotional evolutions within pardon tales and elucidate how emotive factors influenced adjudicative outcomes.
Epistemic Responsibility towards “New” Nations: Making Bangladesh’s Textuality More Visible through Reinventive Digital Metadata
Bhattacharyya, Sayan (1); Rahman, Qazi Arka (2)
1: Yale University, United States of America; 2: West Virginia University, United States of America
We propose innovative digital humanities methodologies to address the invisibility of Bangladeshi textuality, advocating for advanced machine learning over traditional cataloging. This approach, sensitive to the complex socio-historical context of postcolonial societies, aims to better represent nuanced identities, with potential applications across the global South.
Comparative Analysis of the Writing of S.R. Ranganathan and Contemporary Themes of LIS Education: Re-Framing the History of Global Library Scholarship and Pedagogy
Hackney, S.E.; Weinstein, Edison
Queens College, CUNY, United States of America
HTML XMLWe examine the work of S.R. Ranganathan, and the current core competencies for LIS education as published by the ALA. Using data analysis tools and historical research, we pinpoint overlaps in the themes of these two sources, in order to analyze the historical, pedagogical, and theoretical themes of the two.
Reinventing historical source criticism with style and culture. The evidential value of computational authorship analysis and its consequences for data culture in historical scholarship using the example of an alleged autobiography by Adolf Hitler from 1923
Hiltmann, Torsten (1,2); Dröge, Martin (1,3)
1: Humboldt-Universität zu Berlin, Germany; 2: NFDI4Memory; 3: AI-SKILLS
HTML XMLUsing a case of contested authorship from the early Nazi period, this project explores the benefits of data-driven source criticism and discusses its implications for historical research. It emphasizes the data-driven changes in the discipline's practices and highlights the need to discuss and redefine the data culture within the discipline.
Whose alpha is it? Paleographic analysis environment and the building of disciplinary standards
Stoyanova, Simona (1); Noël, Geoffroy (2)
1: University of Oxford, United Kingdom; 2: King's College London, United Kingdom
This paper discusses the re-invention of an environment for palaeographic analysis, as a sustainable, modular and open application. Working on inscriptions of ancient Sicily, in a variety of languages and scripts, studying the development of writing systems in a multilingual and multicultural context.
Reinventing a bio[biblio]graphy as a geodatabase: A temporal map of Ibn Sīnā’s corpus and fields of scholarship, and a geospatial critique of his imagined past in Isfahan
Shahidi Marnani, Pouyan
Indiana University Bloomington, USA
How building a temporal-geospatial database comprised of biobibliographical data of a medieval, travelling polymath and sociopolitical data of his time along with data visualization and analysis in ArcGIS platforms, helped resolving historical complications, contextualizing his work, and examining hypotheses of modern historians regarding his whereabouts in the city of Isfahan.
Quantifying Leninism. Using Multimodal Large Language Models to Detect and Quantify the Depiction of Historic Persons in Visual Contents
Oiva, Mila; Ohm, Tillmann; Karjus, Andres
Tallinn University, Estonia
In this paper we evaluate the applicability of pretrained multimodal Large Language Models (LLM) in a zero-shot learning setup to detect depictions of Lenin in the most important Soviet newsreel series titled “Novosti dnia” (“News of the Day”, 1945-1992).
A statistical analysis of the effects of censorship on the letters of Australian soldiers in World War I
Dennis-Henderson, Ashley Grace; Roughan, Matthew; Tuke, Jonathan
The University of Adelaide, Australia
HTML XMLWhen analysing war letters, one concern is that they may be "sanitised" due to censorship restrictions, and as such are not useful for understanding soldiers' experiences. This work compares Australian World War I letters to diaries to determine if there is a statistically significant difference between them due to censorship.
Toward Understanding Book Rating Divergence across Platforms and Editions:A Preliminary Case Study
Hu, Yuerong (1); Wu, Peizhen (2); Downie, J. Stephen (2)
1: Indiana University Bloomington, United States of America; 2: University of Illinois at Urbana Champaign, United States of America
HTML XMLWhile online book ratings have been broadly studied, the phenomenon of rating divergence across platforms and book editions has not been investigated critically. The preliminary findings of this case study showcase the need for understanding book rating divergences more comprehensively.
Theorizing risk attitudes and rationality using agent based modeling
Koeser, Rebecca Sutton; Buchak, Lara
Princeton University, United States of America
HTML XMLThis poster presents results from applying agent-based modeling to an exploration of risk attitudes and rational decision making in the context of group interaction. We are also interested in the place of agent-based modeling and computational philosophy within the computational humanities.
How can you play this object? 3D modelling and VR as tools for documentation and preservation in performance-oriented collections
Eide, Øyvind; Türkoglu, Enes
Universität zu Köln, Germany
HTML XMLThe process of creating digital models of physical objects can be used to better contextualise culture heritage objects in cultural and historical praxis. The paper will discuss these possibilities based on three examples from a theatre collection.
Design and Construction of the corpus of “Kokinshu-Tōkagami”: An Early Modern Annotated Book on Classical Japanese Poetry Anthology
Kubo, Masako (1); Ichimura, Taro (2); Ogiso, Toshinobu (3,1)
1: The Graduate University for Advanced Studies, SOKENDAI; 2: Kyoto Prefectural University; 3: National Institute for Japanese Language and Linguistics, JAPAN
HTML XML"Kokinshu Tōkagami" (1793) by Norinaga Motoori is an annotated edition of "Kokin Waka-shū" (905). It blends various text styles: 10th-century waka poems, early Middle Ages' literary style, and contemporaneous colloquial language. To create the corpus, XML tags were employed for style differentiation, enabling accurate morphological analysis using multiple dictionaries.
Publishing Process for Digital Scholarly Editing: Jagiellonian Digital Platform
Hałaczkiewicz, Joanna Katarzyna (1); Grabska-Gradzińska, Iwona (1); Komorowska, Magdalena Eulalia (1); Turska, Magdalena (2)
1: Jagiellonian University; 2: e-editiones.org
Jagiellonian Digital Platform brings together scholars and IT developers in order to create a supportive environment for interoperable, accessible and sustainable digital scholarly editions. We want to assist scholarly editors in creating new paths into textual analysis and representation, which they might not envision alone.
Development and Application of hi-glyph: A Chinese Character Glyph Management System
Liu, Guanwei (1); Nakamura, Satoru (2); Yamada, Taizo (2)
1: Institute for Research in Humanities, Kyoto University, Japan; 2: Historiographical Institute, University of Tokyo, Japan
HTML XMLHi-glyph, an open-source web app, efficiently manages non-registered Chinese characters in digitized humanities databases. It overcomes limitations, offering user-friendly character management and enhanced features. Implemented with JavaScript and Next.js, hi-glyph demonstrates efficacy in addressing historical document database challenges, signifying its potential in advancing humanities digitization.
Literary Methods for All: CLS INFRA – Unlocking a World of Words!
Birkholz, Julie (2); Börner, Ingo (3); Byszuk, Joanna (4); Charvát, Vera Maria (5); Cinková, Silvie (6); Dejaeghere, Tess (2); Dijkstra, Anna (7); Dudar, Julia (8); Ďurčo, Matej (5); Eder, Maciej (4); Edmond, Jennifer (9); Fileva, Evgeniia (8); Fischer, Frank (10); Gouzi, Françoise (9); Heiden, Serge (11); Hoover, Sarah (1); Janssen, Maarten (6); Křen, Michal (6); Kunda, Bartłomiej (4); Milling, Carsten (3); Mrugalski, Michał (12); Murphy, Ciara L. (1); Plank, Lukas (5); Raciti, Marco (9); Resch, Stefan (5); Ridge, Emily (1); Ros, Salvador (13); Schöch, Christof (8); Šeļa, Artjoms (4); Sluyter-Gäthje, Henny (3); Tasovac, Toma (14); Tonra, Justin (1); Tóth-Czifra, Erzsébet (9); Trilcke, Peer (3); van Dalen-Oskam, Karina (7); Woldrich, Anna (5); Yakupova, Vera (9)
1: University of Galway, Ireland; 2: Universiteit Gent; 3: Universität Potsdam; 4: Institute of Polish Language (Polish Academy of Sciences); 5: Austrian Academy of Sciences, Austrian Centre for Digital Humanities and Cultural Heritage; 6: Charles University, Prague; 7: Huygens Institute; 8: Universität Trier; 9: DARIAH-EU; 10: Freie Universität Berlin; 11: Ecole Normale Supérieure, Lyon; 12: Humboldt-Universität zu Berlin; 13: UNED Madrid; 14: Belgrade Center for Digital Humanities
Unlock the Power of Literature in the Digital Age with EU-Funded Computational Literary Studies Infrastructure (CLS INFRA)! We are helping to build the shared and sustainable infrastructure needed to reinvent approaches to existing data, tools, and knowledge, revolutionizing the study of Europe’s multilingual literary heritage. Working within the FAIR and CARE principles (Wilkinson et al. 2016; 2019; Carroll et al. 2020) we are standardizing, aligning resources, and widening access for researchers everywhere. The aim is to build on recently-compiled high- quality literary corpora, such as DraCor and ELTeC (Fischer et al. 2019; Schöch et al. 2021; Odebrecht, Burnard, and Schöch 2020), and tools e.g. TXM, stylo, multilingual NLP pipelines (Heiden 2010; Eder, Rybicki, and Kestemont 2016), demonstrating how they can be used by academics and non-academics engaged with all kinds of textual analysis. In the proposed poster we will present the recent achievements and deliverables of the CLS INFRA projects, focusing specifically on the tools and information that make CLS methods accessible to all. Let's create new insights into our diverse European cultural tapestry together!
A Contemplation on Semantic Indexing with Persistent Identifiers
Chuang, Tyng-Ruey
Academia Sinica, Taiwan
We contemplate on the use of persistent identifier systems, in particular the Wikidata, for the semantic indexing of document collections and its implications. We will discuss the issues of semantic drifting, authority control, as well as collaboration and iteration.