Loading Events

« All Events

  • This event has passed.

Workshop on Computational Methods in the Humanities 2022 (COMHUM 2022)

9 June 2022 - 10 June 2022

9-10 June 2022

How to come to the conference. The workshop will take place in room  275 of the Internef building. Please take the metro M1 and leave at station UNIL-CHAMBERONNE. Then it will be a 3 minutes walk. Usually, you get a public transport pass at your hotel reception. If not, you can buy tickets at the metro station or at cff.ch (there is a very useful app too).


Program (version 1 June 2022). The title of paper called “Analyzing Character Networks in Fan Fictions of Archive of Our Own” is now “Analyzing Character Networks in Crossover Fan Fictions of Archive of Our Own”. The program will be updated soon.

In the following list, click on a title to get access to the corresponding abstract (PDF).

Invited keynote
9 juin11hVincent LabatutExtraction and Analysis of Fictional Character Networks [SLIDES (PDF)]
Character Networks – Session 1
9 juin13h30François Bavaud and Coline MétraillerA (dis)similarity index for comparing two character networks
9 juin14hThomas Schmidt, Johannes Hoffmann and Christian WolffAnalyzing Character Networks in Crossover Fan Fictions of Archive of Our Own
9 juin14h30Guillaume GuexRefining Character Relationships in a Narrative using Embeddings of Interactions
Character Networks – Session 2
9 juin15h30Itay Marienberg-Milikowsky and Dan VilenchikHighlighted Gaps: Toward Undogmatic Modeling of Literary Character Networks
9 juin16hColine MétraillerNarrative flow: a formal approach of character network generation for non-linear narratives
9 juin16h30Arthur Amalvy, Vincent Labatut and Richard DufourBERT meets d'Artagnan: Data Augmentation for Robust Character Detection in Novels
Global track – Session 1 – Techniques
10 juin8h30Marion RiggsAdapting FlauBERT for WSD of Eighteenth-Century Aesthetic Terms
10 juin9hSimon Brenner, Timo Frühwirth and Sandra MayerA Computer-Vision Approach to Visualizing ‘Indented’ Poetry by W. H. Auden
10 juin9h30Phillip Benjamin Ströbel, Simon Clematide, Martin Volk and Tobias HodelTransformer-based HTR for Historical Documents
Global track – Session 2 – Uncertainty
10 juin10h30Fabio Mariani“Probably Sold to Paalen, Possibly by Exchange”: Vagueness, Incompleteness, Subjectivity and Uncertainty in Digital Art Provenance
10 juin11hMarilena Daquino, Valentina Pasqual, Francesca Tomasi and Fabio VitaliConjectures: using RDF in critical discourse in the humanities
10 juin11h30Christian WachterDisplays of Conception: Representing Historiographical Models Through Multimodal Publications
Global track – Session 3 – Language
10 juin13h30Bruno Almeida, Rute Costa, Ana Salgado, Margarida Ramos, Laurent Romary, Fahad Khan, Sara Carvalho, Mohamed Khemakhem, Raquel Silva, Toma TasovacModelling usage information in a legacy dictionary: from TEI Lex-0 to Ontolex-Lemon
10 juin14hMarco Passarotti, Francesco Mambrini, Eleonora Litta, Flavio Massimiliano Cecchini, Matteo Pellegrini, Giovanni Moretti, Paolo Ruffolo and Giulia PedoneseThe LiLa Knowledge Base of Interoperable Linguistic Resources for Latin. Architecture and Current State
10 juin14h30Nicole Tamer, Barbara McGillivray and Elizabeth SmithDarwin’s Language Evolution: Detecting Lexical Usage in Darwin’s Correspondence
Global track – Session 4 – Visual
10 juin15h30Fanny Barnabé and Nicolas BourgeoisVocabulary Circulation in French-speaking Video Game Streaming on Twitch.tv: How to Model and Make Interpretable the Intersection between Network Analysis and NLP?
10 juin16hIgor BajenaKnowledge representations of digital reconstruction in 3D models
10 juin16h30Ronja Utescher, Aaron Pattee, Ferdinand Maiwald, Jonas Bruschke, Stephan Hoppe, Sander Münster, Florian Niebling and Sina ZarrießExploring Naming Inventories for Architectural Elements for Use in Multi-modal Machine Learning Applications
Special track: character network construction and analysis

At the turn of the 2020s, a defining characteristic of digital humanities remains the remarkably wide spectrum of viewpoints they encompass, ranging from a pure engineering perspective applied to humanities data to the use of well established humanities research methods to investigate born-digital artifacts. In this framework, the COMHUM workshop series positions itself as an international forum primarily devoted to the following research questions: (1) which computational methods are most appropriate for dealing with the particular challenges posed by humanities research, e.g., uncertainty, vagueness, incompleteness, but also with different positions (points of view, values, criteria, perspectives, approaches, readings, etc.)? And (2) how can such computational methods be applied to concrete research questions in the humanities?

The second edition of the COMHUM workshop will take place on June 9 and 10, 2022 at the University of Lausanne (UNIL), unless the sanitary situation requires organizing the event online. The first day will be devoted to the specific topic of computational methods for constructing and analyzing character networks. This topic has ramifications in a variety of disciplines, including linguistics, literary analysis, digital humanities, and game studies. It is of particular interest for a number of research initiatives at UNIL and in neighboring institutions. COMHUM 2022 will thus be a perfect opportunity to bring together researchers from different communities studying character networks using computational and methodologically explicit approaches, to review the state of the art in this domain and to sketch its future developments.

In the spirit of the first edition of the COMHUM workshop, the second day will be open to submissions on any topic pertaining to theoretical or applied research on computational methods for humanities research broadly conceived.

The program will consist of invited and contributed talks. The official language of the workshop is English. Contributions can be submitted in English or French.


The topics of the workshop are divided into two tracks. The special track focuses on formal and computational aspects related to the development and use of computational methods for character network construction and analysis in data from various media types studied in the humanities, such as literature, movies, comics, and video games for example.

Topics in the special track include, but are not limited to:

  • methods for character network extraction (e.g. NLP, computer vision, etc.)
  • formal definitions and representation of relations in character networks
  • quantitative methods for character network analysis
  • computational methods for large-scale or transmedia studies of character networks

In addition, an open track welcomes submissions on formal and computational aspects related to the development and use of computational methods in the humanities in general (with a particular interest for the disciplines represented in the Faculty of Arts of UNIL – such as literature, linguistics, history, history of art, cinema studies).

Topics in the open track include, but are not limited to:

  • Theoretical issues of formal modeling in the humanities
  • Knowledge representation in the humanities
  • Data structures addressing specific problems in the humanities (including text and markup)
  • Quantitative methods in the humanities (e.g., for literary or historical studies, or for multimodal data)
  • Applications of computer vision, image analysis and spatial analysis in the humanities

Invited Speaker

  • Vincent Labatut, Université d’Avignon [SLIDES]


The workshop will take place in room  275 of the Internef building. Please take the metro M1 and leave at station UNIL-CHAMBERONNE. Then it will be a 3 minutes walk. Usually, you get a public transport pass at your hotel reception. If not, you can buy tickets at the metro station or at cff.ch (there is a very useful app too).

The workshop is organized by members of the Lausanne Lab for Computational and Statistical Text Analysis (https://wp.unil.ch/llist/en): François Bavaud, Guillaume Guex, Coline Métrailler, Davide Picca, Stéphanie Pichot, Michael Piotrowski, Yannick Rochat, Aris Xanthos.

It is hosted by the Department of Language and Information Sciences (https://www.unil.ch/sli), with the support of the Center for Linguistics and the Science of Language (https://www.unil.ch/clsl), both in the Faculty of Arts at UNIL.

The workshop underlines the commitment of the department of Language and Information Sciences to the computational dimension of the digital humanities, including formal and mathematical methods.

Scientific Committee

  • François Bavaud (UNIL, SLI and IGD)
  • Giovanni Colavizza (University of Amsterdam)
  • Guillaume Guex (UNIL, SLI)
  • Coline Métrailler (UNIL, SLI, co-chair)
  • Fabian Moss (University of Amsterdam)
  • Davide Picca (UNIL, SLI)
  • Michael Piotrowski (UNIL, SLI)
  • Yannick Rochat (UNIL, SLI, chair)
  • Elena Spadini (UNIL, CLSR)
  • Mathieu Triclot (Université de technologie de Belfort Montbéliard)
  • Aris Xanthos (UNIL, SLI)

Further Info

Please get in touch with Yannick Rochat (yannick.rochat@unil.ch) or Coline Métrailler (coline.metrailler@unil.ch) for specific questions whose answer may not be found on the website.


We invite researchers to submit abstracts of 500 to 1000 words (excluding references; approx. 1–2 pages in the specified format). Abstracts will be reviewed double-blind by members of the program committee, and all submissions will receive several independent reviews. Abstracts submitted at review stage must not contain the authors’ names, affiliations, or any information that may disclose the authors’ identity.

Authors of accepted abstracts will be invited to present their research at the workshop as a talk, and the abstracts will be published in the book of abstracts of the workshop. The maximum number of submissions by the same author is two papers. An author cannot be the first author of two papers.

Paper submissions must use the official ACL style templates (you can drop the short summary section, which is not relevant here). They are available as an Overleaf template (https://www.overleaf.com/read/crtcwgxzjskr) and also downloadable directly in LaTeX and Word formats (https://github.com/acl-org/acl-style-files). Abstracts must be submitted electronically in PDF format. For the submission of abstracts, we use EasyChair: https://easychair.org/my/conference?conf=comhum2022


After the conference, authors of accepted contributions were invited to submit a full paper version (6–16 pages), which, if accepted after peer-review, would be published in an open-access, electronic conference volume endowed with persistent identifiers.

The result are the COMHUM 2022 Workshop Proceedings, published with CEUR-WS (vol. 3602). This volume contains revised and expanded versions of 7 of the papers presented at the workshop.

We thank CEUR-WS for their support!

Important Dates

  • Deadline for submission of abstracts: January 28, 2022 February 11, 2022
  • Notification of acceptance: February 18, 2022 March 18, 2022
  • Workshop: June 9–10, 2022


9 June 2022
10 June 2022
Event Category:


Laboratoire lausannois d’informatique et statistique textuelle
View Organizer Website


Campus Dorigny
Lausanne, 1015 Suisse
+ Google Map
View Venue Website