Seminar: placing Greek inscriptions with machine learning • 23 May 2023

Event organised by the Computational Humanities research group

23 May 2023 3pm BST (remote)

Thea Sommerschield (Ca’ Foscari University of Venice, Italy), Restoring, dating and placing Greek inscriptions with machine learning: the Ithaca project

Abstract

Ithaca is the first deep neural network for the textual restoration, geographical attribution and chronological attribution of ancient Greek inscriptions. This AI model is designed to assist and expand the historian’s workflow, focusing on collaboration, decision support and interpretability. In this presentation, I will introduce Ithaca and guide you through the model’s architecture, design decisions and visualisation aids. I will also offer a demo of how to use Ithaca for your personal research.

Bio

Thea Sommerschield is a Marie Skłodowska-Curie fellow at Ca’ Foscari University of Venice. Her research uses machine learning to study the epigraphic cultures of the ancient Mediterranean world. Since obtaining her DPhil in Ancient History (University of Oxford), she has been the Ralegh Radford Rome Awardee at the British School at Rome, Fellow in Hellenic Studies at Harvard’s CHS and Research Innovator at Google Cloud. She co-led the Pythia (2019) and Ithaca (2022) projects, and has worked extensively on Sicilian epigraphy.

To register to this seminar, please email Barbara McGillivray at Barbara.mcgillivray@kcl.ac.uk

Seminar: Latin BERT for Word Sense Disambiguation • 16 May 2023

Event organised by the Computational Humanities research group

16 May 2023 3pm BST (remote)

Piroska Lendvai and Claudia Wick (Bavarian Academy of Sciences and Humanities, Germany), Finetuning Latin BERT for Word Sense Disambiguation on the Thesaurus Linguae Latinae

Abstract

The Thesaurus Linguae Latinae (TLL) is a comprehensive monolingual dictionary that records contextualized meanings and usages of Latin words in antique sources at an unprecedented scale. We created a new dataset based on a subset of sense representations in the TLL, with which we finetuned the Latin BERT neural language model (Bamman and Burns, 2020) on a supervised Word Sense Disambiguation task. We observe that the contextualized BERT representations finetuned on TLL data score better than static embeddings used in a bidirectional LSTM classifier on the same dataset, and that our per-lemma BERT models achieve higher and more robust performance than reported by Bamman and Burns (2020) based on data from a bilingual Latin dictionary. We discuss the differences in sense organizational principles between these two lexical resources, and report about our dataset construction and improved evaluation methodology.

Bios

Piroska Lendvai (PhD) works at the Digital Humanities R&D Department of the Bavarian Academy of Sciences and Humanities (Munich, Germany), where she supports research in Humanities and Social Sciences via tools and approaches from language technology.

Claudia Wick (PhD) works as a lexicographer in the Thesaurus linguae Latinae project at the Bavarian Academy of Sciences and Humanities (Munich, Germany) that targets the compilation of a comprehensive dictionary for ancient Latin. In her spare time she pursues programming. To register to this seminar, please email Barbara McGillivray at Barbara.mcgillivray@kcl.ac.uk

Seminar: Historical Language Models and their application to Word Sense Disambiguation • 9 May 2023 3pm

Event organised by the Computational Humanities research group

9 May 2023 3pm BST (remote)

Enrique Manjavacas (Leiden University, The Netherlands), Historical Language Models and their application to Word Sense Disambiguation

Abstract

Large Language Models (LLMs) have become the cornerstone of current methods in Computational Linguistics. As the Humanities look towards computational methods in order to analyse large quantities of text, the question arises as to how these models are best developed and applied to the specificities of their domains. In this talk, I will address the application of LLMs to Historical Languages, following up on the MacBERTh project. In the context of the development of LLMs for Historical Languages, I will address how they can be specifically fine-tuned with efficiency to tackle the problem of Word Sense Disambiguation. In a series of experiments relying on data from the Oxford English Dictionary, I will highlight how non-parametric and metric learning approaches can be an interesting alternative to traditional fine-tuning methods that rely on classifiers that learn to disambiguate specific lemmas.

Bio

Enrique Manjavacas Arevalo is currently a post-doc at the University of Leiden, working in the MacBERTh project developing Large Language Models for Historical Languages. He obtained a PhD at the University of Antwerp (2021) with a dissertation on computational approaches to text reuse detection.

The video of this seminar is available here: https://youtu.be/TnodLOKw-wY.

Museum Analytics: Registration and programme

Organisers: Andrea Ballatore (KCL), Jamie Larkin (Chapman Uni.), with the support of Zhi Ye (Nina) (KCL)

Registration for participants: if you want to attend, please register at this <form>.

Programme

⏱️ When: Thursday 18 May 2023, 10:00 am – 5:30 pm (UK time)

📍 Where (hybrid): King’s College London, Bush House, (S) 1.01 (lecture theatre 1). For registration, please go to the North Entrance (see this map and this photo of the entrance). The link for online participation will be circulated by email before the event.

9:30 – 10:00 • Coffee/registration
10:00 – 10.15 • Introduction by organizers
10:15 – 11:30 • Paper session 1: Data Analytics for Museum Management
11.30 – 11.45 • Coffee break
11:45 – 13:00 • Paper session 2: New Media Ecologies
13.00 – 14.00 • Lunch break
14.00 – 15.15 • Paper session 3: Museum Data Practices
15.15 – 15.30 • Coffee break
15:30 – 16:45 • Paper session 4: Museum Data Infrastructures
16.45 – 17.00 • Comfort break
17.00 – 17:30 • Discussion and activity
17:30 – 17:40 • Closing remarks
17.40 – 18:00 Networking opportunity

Paper session 1: Data Analytics for Museum Management

  • Chair: Dr Mark Liebenrood
  • ‘How Italian museums are facing the digital challenge’
    Mauro De Bari (University of Bari, Italy)
  • ‘Challenges and opportunities for data based museums’
    Pille Runnel, Pille Pruulmann-Vengerfeld & Agnes Aljas (Estonia National Museum, Estonia, & Malmö University, Sweden)
  • ‘What a Wonderful World: designing a media ecosystem at MAXXI museum in Rome’
    Carmen Guarino, Stefano Capezzuto & Daniele Bucci (University of Palermo, Italy & Ecosistemica)

Paper session 2: New Media Ecologies

  • Chair: Dr Chiara Zuanni
  • ‘Sensory Experience as Interaction Data in Exhibition Spaces’
    Izabel Derda (Erasmus University, The Netherlands)
  • ‘Worlding ontologies. Towards more ethical museum databases’
    Mariel Hidalgo-Urbaneja, Athanasios Velios & Paul Goodwin (University of the Arts London, UK)
  • ‘Virtual Acoustic Objects in Museum Environments: Bridging the Inaccessibility of Interactive Cultural Objects’
    Dominik Ukolov (Leipzig University, Germany)
  • ‘Samplebar Kenya and Beyond: On Interactive Ways to Digitise Traditional Music’
    Kahithe Kiiru & Hakan Libdo (Bombas of Kenya & Libido Music AB)

Paper session 3: Museum Data Practices

  • Chair: Dr Serena Iervolino
  • ‘Counting the small majority: correcting sampling bias in online museum studies’
    Ellen Charlesworth (Durham University, UK)
  • ‘Biases in data: the case of online museum catalogues’
    Anna-Maria Sichani (School of Advanced Study, University of London, UK)
  • ‘Enriching Exhibition Scholarship’
    Clare Llewellyn (University of Edinburgh, UK)
  • ‘Unlocking Collection Histories: Provenance Data and Agency’
    Fabio Mariani (Lynn Rother & Max Koss, Leuphana University, Germany)

Paper session 4: Museum Data Infrastructures

  • Chair: Prof Alex Poulovassilis
  • ‘Humanities Research, Museums, and Linked Data’
    Toby Burrows, Deb Verhoeven & Mike Jones (University of Western Australia, University of Alberta, Canada, & Australia National University)
  • “Sloane Lab: Domain Vocabularies for Semantic Interoperability of Museum Collections” Andreas Vlachidis & Daniele Metilli (UCL, UK)
  • ‘Generative AI and the Museum: Working with Collections as Training Data’
    Joel McKim & Alessandro Provetti (Birkbeck, University of London, UK)
  • ‘Unlocking the connective potential of Oral History through Natural Language Processing’ Stefano De Sabbata, Stefania Zardini Lacedelli, Alex Butterworth, Colin Hyde, Sally Horrocks, Neslihan Suzen, (University of Leicester, UK & Science Museum Group)

🍻 Conference pub (from 6 PM): Museum Tavern, 49 Great Russell St, London WC1B 3BA

🍽️ Conference dinner (self-funded): please contact organisers for information

Other information: Call for abstracts: New Directions in Museum Analytics

Contacts

For inquiries, please contact us at andrea.ballatore [at] kcl.ac.uk ✉️

Ten new posts in the Department of Digital Humanities

We are delighted to be announcing ten new permanent academic positions in the Department of Digital Humanities. As many in the community know, DDH has expanded a great deal in the last fifteen years. In this time “the digital”, both in and as related to the humanities, has changed beyond all recognition. As well as revolutionizing the way in which we deal with data, computation and analysis in the humanities, we have seen the rise of the interactive World Wide Web, of social media, the digital economy, and key contemporary issues such as fake news and misinformation. Our philosophy is that none of these ways that “the digital” relate to the “the human” can be researched or taught in isolation; and this has underpinned our expansion. We therefore encourage applications for these posts from across the DH broadly defined. 

This ground-breaking investment both consolidates our research and teaching in key areas of DH including computational humanities, digital content management and digital culture and society; and engages with emergent areas, including AI and society, and race and gender in DH. These appointments will also enable us to expand and improve some of the activities that make the DH student experience at King’s unique, such as our Writing Lab and Coding Lab.

Half of these new roles are offered on the College’s Academic Education Pathway (AEP). For these roles in particular we are looking for colleagues who wish to use their skills, experience and passion in developing and leading our teaching programmes. This includes both our “traditional” undergraduate and postgraduate programmes, and also a new suite of courses we are developing on Continuing Professional Education (CPD) and professional and executive education.

Please feel free to contact the Head of Department, Professor Stuart Dunn (stuart [dot] dunn [at] kcl.ac.uk) for an informal discussion.

Further details on the posts and how to apply may be found in the following links:

DDH researchers contribute chapters to book on “Digital (In)Justice in the Smart City”

Researchers at the Department of Digital Humanities have contributed chapters to a new book on Digital (In)justice in the Smart City on Toronto University Press.

Güneş Tavmen wrote a chapter on “Cybernetic Urbanism: Tracing the Development of the Responsibilized Subject and Self-Organizing Communities in Smart Cities”.

Jonathan Gray co-wrote a piece with Noortje Marres on “Articulating Urban Collectives with Data”.

Here is an excerpt from the book blurb:

In the contemporary moment, smart cities have become the dominant paradigm for urban planning and administration, which involves weaving the urban fabric with digital technologies. Recently, however, the promises of smart cities have been gradually supplanted by recognition of their inherent inequalities, and scholars are increasingly working to envision alternative smart cities.

Informed by these pressing challenges, Digital (In)Justice in the Smart City foregrounds discussions of how we should think of and work towards urban digital justice in the smart city. It provides a deep exploration of the sources of injustice that percolate throughout a range of sociotechnical assemblages, and it questions whether working towards more just, sustainable, liveable, and egalitarian cities requires that we look beyond the limitations of “smartness” altogether. The book grapples with how geographies impact smart city visions and roll-outs, on the one hand, and how (unjust) geographies are produced in smart pursuits, on the other. Ultimately, Digital (In)Justice in the Smart City envisions alternative cities – smart or merely digital – and outlines the sorts of roles that the commons, utopia, and the law might take on in our conceptions and realizations of better cities.

Workshop: “Infrastructuring alternatives: Mastodon, the Fediverse and beyond”, 6th April 2023

We’re looking forward to hosting Roel Roscam Abbing (Malmö University / lurk.org) for a workshop on “Infrastructuring alternatives: Mastodon, the Fediverse and beyond”.

The workshop will take place on 6th April, at King’s College London, Strand Campus. Further details are available below.

Infrastructuring alternatives: Mastodon, the Fediverse and beyond

  • When? 6th of April 2023, 1-5pm
  • Where? Strand Campus, King’s College London

After many years of inaction and, one might say, neglect on the issue of public digital infrastructures,  there is a moment of opportunity in regard to social media systems. The last year saw a marked increase in interest in alternative social media, such as Mastodon, in response to the highly mediatised takeover and subsequent mismanagement of Twitter by Elon Musk. This event served as a sudden wake-up call for different communities which relied on that privatized social infrastructure to, for example, disseminate knowledge.  

This workshop brings together scholars, independent researchers and media activists to consider this moment and what action might look like. The workshop introduces the question of alternative social media and how a software like Mastodon, based on its federated topology, allows for different relationships between user communities and their infrastructures. The workshop introduces the software in a hands-on way, both from use and administrative perspectives, as a way to understand what federation entails. The notion of federation was theorized as an organizational form in which local units agree to share governance to scale up organizational capacity and address larger shared issues, without giving up on local diversity and pluralism. Within alternative social media, the federation implies interoperable but separately managed entities which can set their own policy. However, as yet, they have no way of addressing issues that supersede the level of the local. The question thus posed by the workshop is how to scale and support alternative and public digital infrastructures? What approaches for doing so exist, and what can we imagine?

Due to the format of this workshop there will be a limited number of spaces for this event. If you’re interested in joining please send a note to jonathan.gray@kcl.ac.uk.

This workshop is co-organised by the Centre for Digital Culture, the Digital Futures Institute and the Department of Digital Humanities, King’s College London together with the Critical Infrastructure Studies collective and Centre for Digital Inquiry, University of Warwick.

Image: “Fed up!” poster by Artemis Gryllaki, Bohye Woo and Lídia Pereira.

Video from “Creative AI: Theory and Practice” symposium

In January the Creative AI Lab at King’s College London/Serpentine (Professor Mercedes Bunz and curator Eva Jäger as Lab’s co-founders, Dr Daniel Chávez Heras, PhD student Alasdair Milne, Professor Joanna Zylinska) hosted a one-day symposium supported by the King’s Institute for Artificial Intelligence.

Colleagues from disciplines across King’s were invited to discuss what the concept of ‘creative AI’ means to them and/or to show some specific projects through which it can be enacted.

Videos of the talks are now available here.

New paper: “Visual Models for Social Media Image Analysis: Groupings, Engagement, Trends, and Rankings”

A new article on “Visual Models for Social Media Image Analysis: Groupings, Engagement, Trends, and Rankings” co-authored by DDH researchers Gabriele Colombo, Liliana Bounegru and Jonathan Gray has just been published in the International Journal of Communication (IJOC). It is available as an open access PDF. Here’s the abstract:

With social media image analysis, one collects and interprets online images for the study of topical affairs. This analytical undertaking requires formats for displaying collections of images that enable their inspection. First, we discuss features of social media images to make a case for studying them in groups (rather than individually): multiplicity, circulation, modification, networkedness, and platform specificity. In all, these offer reasons and means for an approach to social media image research that privileges the collection of images as its analytical object. Second, taking the 2019 Amazon rainforest fires as a case study, we present four visual models for analyzing collections of social media images. Each visual model matches a distinctive spatial arrangement with a type of analysis: grouping images by theme with clusters, surfacing dominant images and their engagement with treemaps, following image trends with plots, and comparing image rankings across platforms with grids.

Investigating fossil fuel greenwashing with Global Witness

Researchers at the Department of Digital Humanities contributed to an investigation into “Fossil fuel greenwash” with Global Witness as part of a broader collaboration on the politics of “nature-based solutions”.

Here’s an excerpt from the methodology section:

To examine the companies’ Twitter images, we worked with researchers from the Department of Digital Humanities at Kings College London and the Public Data Lab to collate images tweeted by the companies. This enabled us to review image and content over time, including coupled text.

Each advertisement and image tweet was analysed for subject matter and style. The text and any voiceover or speech were documented together with the item’s themes. These were assessed against the Climate Social Science Network’s definition of greenwashing (‘a variety of misleading communications and practices that intentionally or not, induce false positive perceptions of an organization’s environmental performance’) and the CMA’s Green Claims Code guidance on misleading environmental claims.