Proceedings of the 2nd Huminfra Conference

Selle kollektsiooni püsiv URIhttps://hdl.handle.net/10062/118290

Sirvi

Nüüd näidatakse 1 - 15 15

Digitising the Past: Digital tools to support rock art research and dissemination
(Tartu University Library, 2025) Green, Ashley; Horn, Christian; Potter, Rich; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
As digital applications in cultural heritage and rock art research continue to grow, resources from the Svenskt Hällristningsforskningsarkiv (SHFA) support such work by providing access to valuable data and tools. The SHFA archive includes data from the 17th century onwards and continually digitises the most recent documentation work. In collaboration with the Gothenburg Research Infrastructure for Digital Humanities we have created a platform to share this data with researchers and the public. The SHFA also provides tools and additional resources to visualise and enhance 3D data with Topography Visualisation Toolbox (TVT, https://tvt.dh.gu.se/). This empowers amateurs and professionals working with 3D recordings to improve their results. These visualisations can be used in deep learning workflows which drives the development of AI approaches in archaeology. In this paper, we provide an overview of SHFA’s resources, their use in and beyond rock art research, their role in data dissemination, and future developments.
DigiCURE: Building a Digital Humanities Infrastructure for Preserving and Studying At-risk Cultural Heritage
(Tartu University Library, 2025) Westin, Jonathan; Lindhé, Cecilia; Brodén, Daniel; Tomasini, Matteo; Almevik,Gunnar; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
The preservation of cultural heritage has become a societal, policy, and scientific priority in the context of climate change, armed conflicts, and rapid urbanization. Monuments, archaeological sites, and fragile materials are increasingly at risk of loss or irreversible damage. In response, DigiCURE (Digital Cultural Resilience and Protection) establishes a technologically advanced and institutionally anchored research infrastructure dedicated to the digitization, preservation, and analysis of endangered heritage. The aim of this paper is to present the DigiCURE research infrastructure, providing high-quality tools, expertise, and training to support sustainable digital preservation through multimodal documentation, spatial visualization, and data modeling. Its online platform enables researchers, heritage professionals, and the public to explore, analyze, and annotate complex multimodal datasets with AI-assisted methods, even in cases where physical access is no longer possible. DigiCURE functions as both a national and international hub for innovative research, ensuring the long-term accessibility and resilience of vulnerable cultural heritage.
Shared Engagement in Digital Environments with Extended Reality and Tangible Interaction
(Tartu University Library, 2025) Quintero, Luis; Solsona, Jordi; Pinheiro Braga, António; Björn, Michael; Fors, Uno; Verhagen, Harko; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
Emergent interactive technologies -- such as extended reality (XR) and its related subcategories augmented, virtual and mixed reality-- are increasingly used in interdisciplinary research endeavors. These technologies aim to explore how smart glasses and headsets that overlay digital objects may support the design of collaborative experiences that enhance human interactions in the physical world. In this short paper, we briefly outline the possibilities of immersive technologies for research and how the Extrality Lab at Stockholm University serves as an infrastructure to prototype state-of-the-art solutions that merge physical tangible interaction and virtual environments in novel applications. We also describe how 3D digital tools may be used for research purposes, taking as an example the project SECE, which aims to study novel interactions, technology-supported artistic expressions, and the future of mobile computing in a cross-disciplinary team in Stockholm. More details about the Extrality Lab at https://extralitylab.dsv.su.se/.
A Frame-Semantic Parsing Plugin for Swedish Research Infrastructure
(Tartu University Library, 2025) Dannélls, Dana; Virk, Shafqat; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
We present the development of a frame-semantic parsing plugin for Sparv – an annotation pipeline for Swedish. The plugin integrates a frame-semantic parser into the annotation pipeline, enabling the automatic identification of frames evoked by lexical units and the assignment of frame elements to their corresponding arguments in text. Designed to operate seamlessly within the infrastructure, the plugin takes raw text as input, and outputs semantic role information in a standardized format compatible with other annotation layers. This implementation demonstrates how frame-semantic analysis can be made available as an additional corpus annotation layer, enriching texts with structured semantic representations that go beyond syntactic or lexical features. By providing access to semantic role information, the plugin can support a wide range of research applications, including semantic search, discourse analysis, and investigation of meaning variation in language use.
Building a Vowel: A Bottom-up Guide for Phonetic and Language Learning Sciences
(Tartu University Library, 2025) Ekström, Axel; Song , Runhui; Edlund, Jens; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
We present a guide for building a vowel “from the ground up” using software developed within the HumInfra infrastructure. Using this guide, a user may recreate in a simulation conditions for the production of a given vowel quality. It is summarized step-wise how a midsagittal view of a speaker’s vocal tract may be reduced to a simplistic sequence of two-dimensional segments, which – input into the simulation software TubeN – predicts and recreates the given vowels quality. Our hands-on guide is of interest to students in the linguistic and teaching sciences, and to those teaching speech science in a broader sense.
Towards Shared Standards for Pseudonymization of Research Data
(Tartu University Library, 2025) Volodina, Elena; Dobnik, Simon; Lindström Tiedemann, Therese; Muñoz Sánchez, Ricardo; Szawerna, Maria Irena; Södergård, Lisa; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
The article introduces the key concepts in pseudonymization, summarizes the half-way findings in the project Mormor Karl, and proposes several ways to unify and standardize the field of pseudonymization.
NER som ett källidentifieringsverktyg. Erfarenheter av svenska BERT för digital historia 1.25
(Tartu University Library, 2025) Norrby, Jens; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
The paper explores my experiences of working with Named Entity Recognition (NER) in Swedish parliamentary records. As such, it provides a practical account of my methodology in employing the Swedish BERT and its NER functionality in a historical dataset. It also reflects on the relevance of this case to the broader relationship between digital and traditional intellectual history. The study described used NER to identify the geographical areas and placenames within Swedish parliamentary discourse from 1887 to 1914. Taken together, this list of locations could be used to determine the aggregate frequencies of geographical groupings, in this case predominantly nations. The quantitative findings were subsequently used to navigate the data set and identify the most relevant texts for qualitative, contextual close readings. This paper argues that there are strengths in employing digital tools but maintaining the framework of traditional intellectual history in accordance with ‘digital history 1.25’
Proceedings of the 2nd Huminfra Conference. HiC 2025
(Tartu University Library, 2025) Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
Exploring Patient Organization Periodicals with the Topic Timelines Text Visualization Method
(Tartu University Library, 2025) Skeppstedt, Maria; Maen, Adam; Danilova, Vera; Aangenendt, Gijs; Burchell, Andrew; Söderfeldt, Ylva; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
The text visualization technique Topic Timelines offers a compact visualization to represent the evolution and clustering of topics over time, while also providing direct access to the texts in which these topics appear. In this paper, we describe how Topic Timelines was further developed within the ActDisease project, by adding functionality for generating timelines using different types of topic extraction techniques and connecting the visualization to existing interfaces for the close reading of texts. Additionally, we evaluate how the updated temporal topic overview can support corpus exploration. The experiments were conducted on a digitalized corpus from the ActDisease project, consisting of patient organization periodicals from the Swedish Diabetes Association, published between 1949 and 1990. Timelines were generated based on topics extracted using sentence transformers clustering and integrated with the ActDisease text database interface - a user interface developed for exploring and reading texts digitalized within the project.
A Distant Technology? Experiments with a Generative Model for Retouching Noisy Newspaper OCR
(Tartu University Library, 2025) Brodén, Daniel; Samuelsson, Lisa; Alfter, David; Malmstedt, Johan; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
This paper explores the use of generative models to enhance digitized historical newspaper text. While these models offer new means of addressing noisy OCR, their opaque, probabilistic processes raise epistemological concerns. Within the project The Order of Criticism Revisited, which integrates literary and computational approaches to Swedish criticism, we tested GPT-4o to “retouch” OCR data from the National Library of Sweden using zero-shot prompting. Comparisons with flawed OCR outputs and manually transcribed texts show that the model produced more legible versions, often closer to the originals than the raw OCR. This indicates potential for improving the quality of digitized sources and enabling more robust large-scale analysis. However, drawing on the notions of artificial communication and distant technology, we argue that such models extend analytical capacity while creating perceptual and methodological distance. Their outputs, better seen as probabilistic “retouching” than correction or reconstruction, weaken the link to original sources.
Beyond Big Tech: Alternative Digital Platforms for Collaborative and Participatory Art Historical Research
(Tartu University Library, 2025) Fox, Elizabeth; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
The selection of digital collaboration platforms impacts research participation in international digital humanities projects. This study emerged from practical challenges during the “Ted Stamm: Tags” project, a multi-institutional art historical research initiative transcribing 63 sketchbooks (1973–81) with 675 documented participant contributions. Initial reliance on Google Sheets was discontinued due to ethical concerns regarding policy changes, while the subsequent transition to Microsoft Excel created barriers for external collaborators across different institutional frameworks. This paper investigates alternative collaborative platforms that meet European standards for data sovereignty while supporting multi-institutional research collaboration. The research question asks: What European alternative platforms exist that provide institutional compatibility and GDPR compliance without sacrificing collaborative functionality? Through a case study methodology grounded in Tags transcription project, this paper proposes an evaluation structure and planned comparative assessment of three European platforms: kSuite, LibreOffice, and Proton Drive.
Documenting AI use in humanities research
(Tartu University Library, 2025) Huvila, Isto; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
This paper explores the critical need to document the use of Artificial Intelligence (AI) in humanities research. While AI offers efficiency and analytical power, its application raises concerns about transparency, bias, and reproducibility. Existing documentation frameworks often emphasize technical aspects, overlooking the human and contextual dimensions vital to humanities scholarship. Drawing on cross-disciplinary literature, the paper advocates for integrating paradata (process-related meta-information) to capture both technical and human facets of AI use. It proposes shifting the focus from speculative future needs to documenting the transformation AI is intended to achieve within specific research contexts. Practical strategies include combining automated tools with reflective documentation practices and providing clear explanations of the purpose and expected outcomes of AI use. The paper calls for infrastructural support and a rethinking of documentation sufficiency to enhance understanding, reuse, and accountability in humanities research.
AI pedagogy and new methods for humanities scholars: A reflective case study
(Tartu University Library, 2025) Haffenden, Chris; Sikora, Justyna; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
How can we bridge the divide between large-scale computational approaches to GLAM collections and the close-reading perspectives of humanities scholars? And how might we raise awareness of the possibilities and the limits of AI search systems, which are rapidly reshaping the research landscape even as AI literacy remains uneven? These questions also involve pedagogy: how to design effective forms of methodological outreach. This paper draws on our experience in developing a workshop to showcase multi-modal topic modelling for heritage organisations and researchers. Building on earlier work, we reflect on design choices in using Google Colab, especially balancing technical depth with accessibility. Our case study highlights the importance of flexible formats that foster critical engagement with AI methods while recognising the limits of short-term interventions.
Boosting up the sentiment analysis models’ accuracy by blending multi-label learning with a large sentiment lexicon
(Tartu University Library, 2025) Kokkinakis, Dimitrios; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
This study compares sentiment analysis approaches for Swedish texts using a manually annotated gold-standard dataset. Two methods were examined: i) a multi-label sentiment classifier trained for Swedish, and ii) the Swedish version of VADER, a lexicon-based tool that computes sentiment scores from a vocabulary of polarity-weighted words. The analysis also examined agreement and disagreement between the two methods, with a focus on mixed or context-dependent sentiment. Results indicate that the multi-label classifier aligns more closely with human judgments, especially for medium- or long-text segments with complex or subtle emotional tones. VADER, while prone to errors in idiomatic or nuanced expressions, performs reliably on short, informal utterances, offering computational efficiency and transparency. A hybrid approach combining classifier predictions with lexicon-based scores was investigated to leverage their complementary strengths. Findings underscore the value of rigorous evaluation against human annotations and highlight strategies to improve sentiment analysis in under-resourced languages such as Swedish.
Mapping Soundscapes of Warning: Experimental Interfaces for Public Sound Culture
(Tartu University Library, 2025) Malmstedt, Johan; Mitsurov, Kirill; Cronqvist, Marie; Nermo, Magnus; Papadopoulou Skarp, Frantzeska; Tienken, Susanne; Widholm, Andreas; Blåder, Anna
This short paper introduces Soundscapes of Warning, an experimental research application designed to support the comparative study of public warning signals as cultural and aesthetic artefacts. Developed through a collaboration between Linköping University and the C2DH at the University of Luxembourg, the platform enables users to explore how alarm sounds -– sirens and civil alert signals – vary across national and historical contexts. By combining geographic comparison with custom-designed 3D visualizations of alarm signals, the application offers a new model for investigating how warnings, urgency, and authority have been rendered sonically in different societies. Instead of approaching warning sounds as purely functional or technical signals, the platform emphasizes their role in shaping public space, perception, and memory. Designed as both a research tool and an interpretive interface, Soundscapes of Warning contributes to current efforts in the digital humanities to critically engage with sound as a mediated and historically contingent form.

Sirvi

Sirvi Proceedings of the 2nd Huminfra Conference Kuupäev järgi