Digital Humanities Synergies

Table Of Contents

• Cover
• Title Page
• Copyright Page
• Table of Contents
• SECTION 1 Language-Related Digital Humanities
• Recent Applications of GermaNet in the Digital Humanities (Erhard Hinrichs)
• 1. Introduction
• 2. Computational Literary Studies
• 2.1. Use Case 1: Identifying Figures or Characters in German Novels
• 2.2. Use Case 2: Identifying Figures or Characters in Dystopian Fiction
• 3. Semantic Search
• 3.1. Use Case 3: Levering Synonym Information From GermaNet in WiTTFind
• 3.2. Use Case 4: Semantic Search in the DWDS Dictionary
• 3.3. Use Case 5: Automatic Crossword Puzzle Generation With GermaNet
• 4. Conclusion
• 5. Acknowledgments
• References
• Vade Mecum on Digital Humanities in Romania: Available Resources and Their Applicability (Mădălina Chitez, Roxana Rogobete, and Adrian Cîntar)
• 1. Introduction
• 2. Digital Humanities Resources Relevant for the Romanian Language and Culture
• 2.1. European Resources
• 2.2. National Resources
• 2.3. Other Resources
• 3. An Example of a Typical Romanian DH Platform: Deportați în Bărăgan
• 4. Conclusions
• References
• Profiling Subgenre Signals in a Collection of Romanian Novels With StyloR (Roxana Patras and Lucreția Pascariu)
• 1. Introduction: The Concept of “Style” and the Recent Traction of Stylometry
• 2. Description of the Collection and Decisions on Preprocessing
• 3. Results
• 4. Conclusions
• References
• Written Expression, Interlanguage, and Catalan as an Additional Language: An Approach From a Learner Corpus (Elga Cremades)
• 1. Introduction: The Influence of First Language on Additional Language Learning
• 2. Conceptual Framework: The Concept and Classification of Errors
• 3. Research Questions
• 4. Participants’ Characteristics
• 5. Corpus
• 6. Data Analysis and Error Classification
• 7. Results and Discussion
• 8. Spelling
• 9. Morphology and Syntax
• 10. Lexicon and Semantics
• 11. Pragmatics and Discourse
• 12. Conclusions
• References
• Digital Landscapes in Comparative Literature: An Experience With Literary Archives (Gabriela Glăvan)
• 1. Introduction
• 2. The New Digital Life of a Problematic Literary Archive
• 3. Conclusion
• References
• Assessing the Readability of Romanian L1 & English L2 Undergraduate Literary Analyses. A Contrastive Approach (Alexandru Oravițan, Mădălina Chitez, and Roxana Rogobete)
• 1. Introduction
• 2. Methods
• 2.1. Assessing Readability
• 2.1.1. Flesch Reading-Ease Score (FRES)
• 2.1.2. Läsbarhetsindex (LIX)
• 2.2. Corpus
• 2.3. Tools
• 3. Results
• 4. Discussion and Conclusions
• 5. Data Availability Statement
• 6. Funding Statement
• References
• Expressing the Sense of Belonging in the Digital World (Mira Bekar and Andrijana Kjose)
• 1. Introduction
• 2. Definitions and Previous Research
• 2.1. Emoji
• 2.2. Sense of Belonging
• 3. Context and Methods
• 4. Data Analysis and Results
• 5. Conclusions and Discussion
• References
• SECTION 2 NLP Outreach
• The Perspectivist Turn in NLP: A Paradigm Shift for Understanding Subjective Language (Claudiu Creangă and Liviu P. Dinu)
• 1. Position
• 2. Introduction
• 3. A Perspectivist Workflow
• 3.1. Soft Label Classification
• 3.2. Multilabel Categorical Classification
• 3.3. Ensemble Learning
• 4. Philosophical Roots of Perspectivism
• 5. Subjectivity and Interpretation
• 6. Recommendations
• 7. Conclusion
• References
• Fanfiction Analysis: Human Versus AI-Generated Texts (Anca Dinu and Andra-Maria Florescu)
• 1. Introduction
• 1.1. What is Fanfiction?
• 1.2. Scope of the Paper
• 2. Data Extraction and Preprocessing
• 3. Analysis
• 3.1. Quantitative Analysis
• 3.2. Qualitative Analysis
• 4. Conclusions
• 5. Limitations
• References
• Building an Entity Linking Dataset for Romanian (Raluca Tudor and Sergiu Nisioi)
• 1. Introduction
• 2. Building the Dataset
• 3. Corpus Analysis—Geopolitical Bias
• 4. Entity Linking System
• 5. Fine-Tuning BERT for Entity Linking
• 6. Evaluation
• 7. Relation to Previous Work
• 8. Conclusions and Future Work
• 9. Limitations
• References
• Machine Translation—Friend or Foe for Academics? (Loredana Mihaela Pungă and Alina-Ștefania Rădoi)
• 1. Introduction
• 2. Research Background
• 3. Research Design
• 3.1. Source Text
• 3.2. Digital Tools
• 3.2.1. Machine translation systems
• 3.2.2. CATMA
• 3.3. Error Typology
• 3.4. Method
• 3.4.1. Fluency
• 3.4.2. Accuracy
• 3.4.3. Fitness for purpose
• 4. Results
• 4.1. Overall Results
• 4.2. Translation System-Specific Results
• 4.2.1. DeepL Translation Errors
• 4.2.2. Google Translate Translation Errors
• 4.2.3. Bing Microsoft Translator Translation Errors
• 5. Conclusion
• References
• Beyond the Headlines: Investigating Linguistic Variation in Romanian Fake News and Non-Fake News Corpora (Iulia Arion, Anca Dinu, and Livia Măgureanu)
• 1. Introduction
• 2. Literature Review
• 3. Data
• 4. Methods
• 5. Analysis
• 6. Classification Task
• 7. Conclusion
• References
• Automatic Processing of Real-Time Recorded Writing: Pausal Segmentation Versus Chunking (Georgeta Cislaru, Iris Eshkol-Taravella, and Sarah Almeida-Barreto)
• 1. Introduction
• 2. Data and Methodology
• 3. Results
• 3.1. The Configuration Chunk+Pause+Chunk
• 3.2. The Configuration POS+Pause+POS
• 3.3. The Case of Chunks Broken by a Pause
• 4. Discussion and Conclusions
• References
• SECTION 3 Culture, History, and Society
• Extracting, Querying, and Visualizing Olfactory Information (Sara Tonelli, Stefano Menini, and Elisa Leonardelli)
• 1. Introduction
• 2. Data
• 3. Method
• 3.1. Description of System for Multilingual Olfactory Information Extraction
• 3.2. Description of Notebooks in the Smell Trend Analyzer
• 4. Analysis of “Rose” Perception Shifts
• 4.1. Smell Source Distribution Over Time
• 4.2. Co-occurrence Analysis
• 4.3. PMI-Based Extraction of Qualities
• 4.4. Co-occurrence Analysis Between Smell Sources
• 5. Conclusions
• 6. Acknowledgment
• References
• The Word “Breathing” in Romanian: Google Search and YouTube Contexts (Eugen Istodor)
• 1. Introduction or Some “Products” of Breathing in the Romanian Media Sphere
• 2. Breathing—A Theoretical Respite
• 3. “Breathing” in Google Search, YouTube, and Apps Contexts
• 4. Conclusions
• References
• Digital Histories of Philosophy and Science: The Early Modern Period (Mihnea Dobre)
• 1. Introduction: Digital Humanities and the Early Modern Studies
• 2. Text Mining on Digital Corpora
• 3. Visualizations
• 4. Networks
• 5. Discussion and Conclusion
• 6. Acknowledgments
• References
• Approaches and Challenges in Applying Network Analysis to Late Antique Letter Collections Case Studies: The Social Networks of the Cappadocian Fathers and Jerome of Stridon (Andra Jugănaru)
• References
• A Digital Approach to the Ancient Greek Lexicon: What’s New? (Constantin Georgescu, Simona Georgescu, and Theodor Georgescu)
• 1. Introduction and Related Work
• 2. Methodology
• 2.1. Digital Database
• 2.2. Search Engine
• 2.3. Lexicographic Software
• 2.4. Manually Processing the Data
• 3. Conclusions
• References
• A Neutrosophic-Based Approach to Identify Young People’s Educational Attitudes and Behavior Toward Active Engagement (Mihaela Colhon, Monica Tilea, and Alina Reșceanu)
• 1. Introduction
• 2. Data Collection Instrument: The “Mindchangers” Questionnaire
• 3. Data Analysis: The Neutrosophic Model
• 4. Conclusions
• 5. Acknowledgments
• References

Anca Dinu, Mădălina Chitez, Liviu Dinu and Mihnea Dobre (eds.)

Digital Humanities Synergies

Disciplines, Methods, and Applications

Berlin · Bruxelles · Chennai · Lausanne · New York · Oxford

Bibliographic Information published by the Deutsche Nationalbibliothek

The Deutsche Nationalbibliothek lists this publication in the Deutsche Nationalbibliografie; detailed bibliographic data is available in the internet at http://dnb.d-nb.de.

Library of Congress Cataloging-in-Publication Data

Names: Dinu, Anca editor | Chitez, Madalina, 1977- editor | Dinu, Liviu editor | Dobre, Mihnea editor

Title: Digital humanities synergies : disciplines, methods, and applications / Anca Dinu, Madalina Chitez, Liviu Dinu, Mihnea Dobre (eds.).

Description: Berlin ; New York : Peter Lang, [2025] | Includes bibliographical references and index

Identifiers: LCCN 2025023546 (print) | LCCN 2025023547 (ebook) | ISBN 9783631923429 hardcover | ISBN 9783631923450 pdf | ISBN 9783631923467 epub

Subjects: LCSH: Digital humanities

Classification: LCC AZ105 .D5443 2025 (print) | LCC AZ105 (ebook)

LC record available at https://lccn.loc.gov/2025023546

LC ebook record available at https://lccn.loc.gov/2025023547

Cover illustration: © Cristina Onet, member of CODHUS Research Centre.

The publication of the volume was supported by the CODHUS Research Centre (Centre for Corpus Related Digital Approaches to Humanities) of the Faculty of Letters, History, Philosophy and Theology at the West University of Timisoara, Romania.

ISBN 978-3-631-92342-9 (Print)

ISBN 978-3-631-92345-0 (ePDF)

ISBN 978-3-631-92346-7 (ePUB)

DOI 10.3726/b22108

© 2025 Peter Lang Group AG, Lausanne (Switzerland)

Published by Peter Lang GmbH, Berlin (Germany)

info@peterlang.com

All rights reserved.

All parts of this publication are protected by copyright.

Any utilization outside the strict limits of the copyright law, without the permission of the publisher, is forbidden and liable to prosecution. This applies in particular to reproductions, translations, microfilming, and storage and processing in electronic retrieval systems.

This publication has been peer reviewed.

www.peterlang.com

Table of Contents

SECTION 1 Language-Related Digital Humanities

Recent Applications of GermaNet in the Digital Humanities

Erhard Hinrichs

Vade Mecum on Digital Humanities in Romania: Available Resources and Their Applicability

Mădălina Chitez, Roxana Rogobete, and Adrian Cîntar

Profiling Subgenre Signals in a Collection of Romanian Novels With StyloR

Roxana Patras and Lucreția Pascariu

Written Expression, Interlanguage, and Catalan as an Additional Language: An Approach From a Learner Corpus

Elga Cremades

Digital Landscapes in Comparative Literature: An Experience With Literary Archives

Gabriela Glăvan

Assessing the Readability of Romanian L1 & English L2 Undergraduate Literary Analyses. A Contrastive Approach

Alexandru Oravițan, Mădălina Chitez, and Roxana Rogobete

Expressing the Sense of Belonging in the Digital World

Mira Bekar and Andrijana Kjose

SECTION 2 NLP Outreach

The Perspectivist Turn in NLP: A Paradigm Shift for Understanding Subjective Language

Claudiu Creangă and Liviu P. Dinu

Fanfiction Analysis: Human Versus AI-Generated Texts

Anca Dinu and Andra-Maria Florescu

Building an Entity Linking Dataset for Romanian

Raluca Tudor and Sergiu Nisioi

Machine Translation—Friend or Foe for Academics?

Loredana Mihaela Pungă and Alina-Ștefania Rădoi

Beyond the Headlines: Investigating Linguistic Variation in Romanian Fake News and Non-Fake News Corpora

Iulia Arion, Anca Dinu, and Livia Măgureanu

Automatic Processing of Real-Time Recorded Writing: Pausal Segmentation Versus Chunking

Georgeta Cislaru, Iris Eshkol-Taravella, and Sarah Almeida-Barreto

SECTION 3 Culture, History, and Society

Extracting, Querying, and Visualizing Olfactory Information

Sara Tonelli, Stefano Menini, and Elisa Leonardelli

The Word “Breathing” in Romanian: Google Search and YouTube Contexts

Eugen Istodor

Digital Histories of Philosophy and Science: The Early Modern Period

Mihnea Dobre

Approaches and Challenges in Applying Network Analysis to Late Antique Letter Collections Case Studies: The Social Networks of the Cappadocian Fathers and Jerome of Stridon

Andra Jugănaru

A Digital Approach to the Ancient Greek Lexicon: What’s New?

Constantin Georgescu, Simona Georgescu, and Theodor Georgescu

A Neutrosophic-Based Approach to Identify Young People’s Educational Attitudes and Behavior Toward Active Engagement

Mihaela Colhon, Monica Tilea, and Alina Reșceanu

Recent Applications of GermaNet in the Digital Humanities

Erhard Hinrichs

Abstract: Usability studies in a wide range of Digital Humanities (DH) applications are presented that demonstrate the added value of integrating semantic information from wordnets. More specifically, the usability studies focus on GermaNet (Henrich and Hinrichs 2010), the wordnet for German that has been under development at the University of Tübingen since 1993. GermaNet is stored as part of the CLARIN research infrastructure in the TALAR repository of the CoreTrustSeal certified CLARIN B-Center at Tübingen University.¹ Access to GermaNet is provided free of charge for academic use; commercial licenses are also available.² GermaNet covers the base vocabulary of contemporary German and has been extended based on word frequency lists that are derived from large digital corpora. Several use cases from recent DH studies for German are surveyed that range from computational literary studies to computational lexicography, semantic information retrieval, and language learning and that have all benefited from the integration of GermaNet information.