From the contemporary observer's perspective, uncertainty seems to have become the rule rather than the exception. Pandemic disaster management, global energy crisis, and geopolitical and nancial instability are all indicators that societal entropy - in the Shannonian sense - continues to rise. For the Computational Humanities Research (CHR) community and conference, the state of uncertainty has been a given since the rst workshop in 2020 which coincided with the emergence of the global pandemic of the coronavirus disease. COVID-19 forced the conference into a virtual mode of meeting, which (almost) became a tradition with the 2021 online CHR conference. As a community that prides itself on being computationally literate, we were well-prepared for a virtual mode, yet the possibility of a physical conference has surfaced on many occasions. With the third iteration of CHR, we transition into a predominantly physical mode of being - with an online option - when we will assemble on December 12-14, 2022, at the beautiful Monastery of the Grauwzusters in Antwerp, Belgium, under the auspices of the University of Antwerp. The physical conference is when taken together with the quality and quantity of submissions, a testament to CHR's status as a valuable and resilient contribution to sociocultural and historical research. With the 2022 edition, we consolidate our community of Humanities researchers with an orientation toward formal and computational approaches. Here the city of Antwerp can serve as an 'aspirational anchor' because just as it serves as the starting point of one of the greatest monuments of road cycling, the Ronde van Vlaanderen, we can aspire to become a monument of Humanities research that enables research talent to solve arduous and formidable problems. As already indicated, we are exceedingly happy with the quality and quantity of conference submissions. Each of the 49 submitted papers was carefully peer-reviewed by a minimum of two researchers drawing on the domain expertise of 77 Program Committee members. We were pleased to be able to accept 29 papers, which were nicely balanced across 15 short and 14 long papers. This year's acceptance rate of 59.2% was similar to the one of last year. The
v call for papers was this year extended with the option to submit a poster, which resulted in the acceptance of 4 posters out of the 6 submitted. As in the previous editions of CHR, many more high-quality papers were submitted than could ultimately be accommodated. It attests to the continued popularity of and enthusiasm for the conference. With regard to demographic parity, we must admit that we are not quite there yet. To attain gender parity in particular still requires some e ort on our side with only31% of the accepted papers being rst-authored by women. On the other hand, many papers are written by graduate students and early career researchers, which shows the inclusivity and openness of our community.
In terms of content, the published papers cover a range of topics and approaches. Problems originating in historical research areas are prevalent as is the reliance on linguistic data and learning-based approaches to structuring natural language. Temporal change in sociocultural systems and the role of dynamics in formal modeling are also becoming recurrent themes, and we continue to see theoretic commitments to information theory and Bayesian statistics. This year two keynotes speakers – Nina Tahmasebi (University of Gothenburg and currently PI of Change is Key!) and Peter Turchin (Emeritus Professor at UConn and founder of Cliodynamics) – re ect these deep interests in understanding change as a fundamental condition of historical and contemporary sociocultural phenomena. The program included below will give a sense of many diverse approaches to this and related problems in the eld of computational humanities research.
If the rst two editions of CHR weren’t such a success, CHR2022 would never have seen the light of day. We are therefore indebted to the organizers of the previous editions for their work and commitment. We wish to address very special thanks to Folgert Karsdorp, Melvin Wevers, and Mike Kestemont, since their experience in organizing earlier editions of CHR and their help in organizing this year’s conference has been invaluable and indispensable.
Furthermore, we are very grateful to the members of the program committee for their time and e orts in reviewing the submitted papers and helping build the program. We also thank the maintainers of the EasyChair conference system for providing a platform that handles the submission and review process, as well as the CEUR-WS.org team for o ering a free open access publication service. We are thankful to all authors who submitted to the conference for contributing their scienti c involvement. We would like to thank our keynote speakers in advance for what will undoubtedly be an inspiring intellectual exchange, to which we all are very much looking forward. Thanks and welcome to all!
CHR2022 was a three-day conference held in Antwerp, Belgium, on December 12 to 14, 2022. Contributions were organized into 7 sessions, as follows:
• Ground-truth Free Evaluation of HTR on Old French and Latin Medieval Literary Manuscripts
Thibault Clérice • Automatic identi cation and classi cation of portraits in a corpus of historical photographs
Taylor Arnold, Lauren Tilton and Justin Wigard • Page Layout Analysis of Text-heavy Historical Documents: a Comparison of Textual and Visual Approaches
Sven Najem-Meyer and Matteo Romanello • The Computational Memorability of Iconic Images
Lisa Saleh and Nanne van Noord
• The Roots of Doubt. Fine-tuning a BERT Model to Explore a Stylistic Phenomenon
Margherita Parigini and Mike Kestemont • Linguistic value construction in 18th-century London auction advertisements: a quantitative approach
Alessandra De Mulder, Lauren Fonteyn and Mike Kestemont • Introducing functional diversity: a novel approach to lexical diversity in (historical) corpora
Folgert Karsdorp, Enrique Manjavacas and Lauren Fonteyn • Detecting Formulaic Language Use in Historical Administrative Corpora
Marijn Koolen and Rik Hoekstra
• Right-wing Mnemonics
Phillip Stenmann Baun and Kristo er Nielbo • Emodynamics: Detecting and Characterizing Pandemic Sentiment Change Points on Danish Twitter
Rebekah Baglini, Kristo er Nielbo, Sara Møller Østergaard and Stine Nyhus Larsen • Di erentiating Social Media Texts via Clustering
Hannah J. Seemann and Tatjana Sche er
• What shall we do with the unseen sailor? Estimating the size of the Dutch East India Company using an unseen species model
Melvin Wevers, Folgert Karsdorp and Jelle van Lottum • Lost Manuscripts and Extinct Texts: A Dynamic Model of Cultural Transmission
Jean-Baptiste Camps and Julien Randon-Furling • Chronicling Crises: Event Detection in Early Modern Chronicles from the Low Countries
Alie Lassche, Jan Kostkan and Kristo er Nielbo • Measuring Rhythm Regularity in Verse: Entropy of Inter-Stress Intervals
Artjoms e, al and Mikhail Gronas • Detecting Sequential Genre Change in Eighteenth-Century Texts
Jinbin Zhang, Yann Ryan, Iiro Rastas, Filip Ginter, Mikko Tolonen and Rohit Babbar
• Gender and Power in Japanese Light Novels
Xiaoyun Gong, Yuxi Lin, Ye Ding and Lauren Klein • A quantitative study of ctional things
Andrew Piper and Sunyam Bagga • Reviewer Preferences and Gender Disparities in Aesthetic Judgments
Ida Marie S. Lassen, Yuri Bizzoni, Telma Peura, Mads Rosendahl Thomsen and Kristo er Nielbo • One Graph to Rule them All: Using NLP and Graph Neural Networks to analyse Tolkien’s Legendarium
Vincenzo Perri, Lisi Qarkaxhija, Albin Zehe, Andreas Hotho and Ingo Scholtes • Modeling Plots of Narrative Texts as Temporal Graph Networks
Leonard Konle and Fotis Jannidis • The process of imitatio through stylometric analysis: the case of Terence’s Eunuchus
Andrea Peverelli, Marieke van Erp and Jan Bloemendal • Determining author or reader: A statistical analysis of textual features in children’s and adult literature
Lindsey Geybels • ‘Entrez!’ she called: Evaluating Language Identi cation Tools in English Literary Texts
Erik Ketzan and Nicolas Werner • Correlations between GoodReads Appreciation and the Sentiment Arc Fractality of the Grimm brothers’ Fairy Tales Yuri Bizzoni and Kristo er Nielbo
• Boosting word frequencies in authorship attribution
Maciej Eder • What Do We Talk About When We Talk About Topic?
Joris van Zundert, Marijn Koolen, Julia Neugarten, Peter Boot, Willem van Hage and Ole Mussmann • Peeking Inside the DH Toolbox – Detection and Classi cation of Software Tools in DH Publications
Nicolas Ruth, Andreas Niekler and Manuel Burghardt • Good Omens: the nice and accurate stylometric analysis
Leonardo Grotti, Mona Allaert and Patrick Quick Programme Chairs • Kristo er Nielbo,Aarhus University • Alie Lassche, Leiden University Organizers • Folgert Karsdorp, KNAW Meertens Institute (general organisation, conference program, proceedings) • Mike Kestemont, University of Antwerp (local organisation) • Alie Lassche, Leiden University (general organisation, conference program, communication, proceedings) • Kristo er Nielbo,Aarhus University (general organisation, conference program, proceedings) • Line Ejby Sørensen, Aarhus University (communication) • Melvin Wevers, University of Amsterdam (general organisation, conference program, communication) Local Organization • Mona Allaert, University of Antwerp • Nooshin Shahidzadeh Asadi, University of Antwerp • Josip Batinic, University of Antwerp • Lamyk Bekius, University of Antwerp • Paavo van der Eecken, University of Antwerp • Wouter Haverals, University of Antwerp • Mike Kestemont, University of Antwerp • Lith Lefranc, University of Antwerp • So e Moors,University of Antwerp • Thomas Smits, University of Antwerp • Lorren Verreyen, University of Antwerp Best Paper Committee • Maud Ehrmann, École Polytechnique Fédérale de Lausanne • Margherita Fantoli, KU Leuven • Folgert Karsdorp, KNAW Meertens Institute • Enrique Manjavacas, Leiden University • Iza Romanowska, Aarhus University • Anne Kandler, Max Planck Institute for Evolutionary Anthropology • Folgert Karsdorp, KNAW Meertens Institute • Mike Kestemont, University of Antwerp • Kristian Gade Kjelmann, Aalborg University • Lauren Klein, Emory Unversity • Ross Kristensen-McLachlan, Aarhus University • Alie Lassche, Leiden University • Cynthia Liem, Delft University of Technology • Cerstin Mahlow, ZHAW Zurich University of Applied Sciences • Eetu Mäkelä, University of Helsinki • Enrique Manjavacas, Leiden University • Barbara McGillivray, King’s College London • George Mikros, National and Kapodistrian University of Athens • David Mimno, Cornell University • Jean-Philippe Moreux, Bibliothèque nationale de France • Coline Métrailler, UNIL • Clemens Neudecker, Berlin State Library • Kristo er Nielbo,Aarhus University • Damien Nouvel, INaLCO • Marco Passarotti, Catholic University of the Sacred Heart • Michael Piotrowski, University of Lausanne • Andrew Piper, McGill University • Thierry Poibeau, LaTTiCe-CNRS • Nils Reiter, Institute of Natural Language Processing, Stuttgart University • Allen Riddell, Indiana University Bloomington • Ramona Roller, ETH Zurich • Matteo Romanello, Ecole Polytechnique Fédérale de Lausanne • Iza Romanowska, Aarhus University • Laurent Romary, INRIA & HUB-ISDL • Yann Ryan, University of Helsinki • Artjoms e, al, Institute of Polish Language, Polish Academy of Sciences (Krakow) • Christof Schoech, University of Würzburg • Marijn Schraagen, Utrecht University • Stefen Schweter, Bayerische Staatsbibliothek München, Munich Digital Library • Roel Smeets, Radboud University • Oleg Sobchuk, Max Planck Institute for the Science of Human History • Rachele Sprugnoli, Università degli Studi di Parma • Nikki Stevens, Arizona State University • Zachary Stine, University of Central Arkansas • Nina Tahmasebi, University of Gothenburg • Tim Tangherlini, Berkeley • Mikko Tolonen, University of Helsinki • Inna Uglanova, Technical University of Darmstadt • Ted Underwood, University of Illinois at Urbana-Champaign • Melvin Wevers, University of Amsterdam • Bruna Wundervald, Maynooth University • Joris van Zundert, KNAW Huygens Institute