Accepted Papers

Accepted Full Papers

  • Semantically Orthogonal Framework for Citation Classification: Disentangling Intent and Content - Changxu Duan (Technische Universität Darmstadt); Zhiyin Tan (L3S Research Center)
  • EUR-Lex-Triples: A Legal Relation Extraction Dataset from European Legislation - Nihed Bendahman (Berger-Levrault/IRIT); Karen Pinel-Sauvagnat (IRIT); Gilles Hubert (IRIT); Mokhtar Boumedyen Billami (Berger-Levrault)
  • Studying Biases in LLMs for Multilingual Historical Newspaper Extraction; The Messina Earthquake Case Study - Sarah Oberbichler (Leibniz Institute of European History); Johanna Mauermann (University of Mainz); The Trung Tran (University of Science and Technology of Hanoi); Carlos-Emiliano González-Gallardo (Université de Tours)
  • The Claims Network: Collecting Research, Education, Impact, and Leadership Claims on the Decentralized Web - Patrick Hochstenbach (Ghent University); Herbert Van de Sompel (DANS); Ruben Verborgh (Ghent University - IMEC)
  • Generating Synthetic Data with Large Language Models for Low-Resource Sentence Retrieval - Davide Caffagni (University of Modena and Reggio Emilia); Federico Cocchi (University of Modena and Reggio Emilia); Anna Mambelli (University of Modena and Reggio Emilia); Fabio Tutrone (University of Palermo); Marco Zanella (University of Padua); Marcella Cornia (University of Modena and Reggio Emilia); Rita Cucchiara (University of Modena and Reggio Emilia)
  • Human-In-The-Loop Workflow for Neuro-Symbolic Scholarly Knowledge Organization - Lena John (TIB-Leibniz Information Centre for Science and Technology); Ahmed Malek Ghanmi (Leibniz University Hannover); Tim Wittenborg (L3S Research Center); Sören Auer (TIB-Leibniz Information Centre for Science and Technology); Oliver Karras (TIB-Leibniz Information Centre for Science and Technology)
  • HistoryCLIP: Adaptive Multi-Modal Retrieval of Imbalanced Long-Tailed Archival Data - Farid Alijani (Tampere University); Elina Late (Tampere University); Sanna Kumpulainen (Tampere University)
  • An end-to-end pipeline for knowledge graph population from 19th-century land registry digitised tables - Solenn Tual (LASTIG, Univ. Gustave Eiffel, IGN-ENSG); Nathalie Abadie (LASTIG, Univ. Gustave Eiffel, IGN-ENSG); Joseph Chazalon (LRE, EPITA); Bertrand Duménieu (CRH, EHESS-CNRS); Julien Perret (LASTIG, Univ. Gustave Eiffel, IGN-ENSG)
  • Heterogeneous Graph Representation for Dataset Link Prediction on Dynamic and Sparse Scholarly Graphs - Ornella Irrera (University of Padua); Matteo Lissandrini (University of Verona); Daniele Dell'Aglio (Aalborg University); Gianmaria Silvello (University of Padova)
  • Neuro-symbolic Federated Research Artifact Search - Farhana Keya (Leibniz Information Centre for Science and Technology); Sören Auer (Leibniz Information Centre for Science and Technology); Mohamad Yaser Jaradeh (L3S Research Center, Leibniz University of Hannover)
  • Organising Knowledge from Text: Prompt-Based Triple Extraction and Graph Enrichment with Large Language Models - Durgesh Nandini (University of Bayreuth); Simon Blöthner (University of Bayreuth); Mario Larch (University of Bayreuth); Mirco Schönfeld (University of Bayreuth)
  • How Retracted Article Persists on YouTube: Retraction Severity, Visibility, and Disclosure - Jiro Kikkawa (Wakayama University); Masao Takaku (University of Tsukuba)
  • Data Discovery using LLMs - A Study of Data User Behaviour - Christin Kreutz (TH Mittelhessen - University of Applied Sciences); Anja Perry (GESIS); Tanja Friedrich (German Aerospace Center)
  • From raw affiliations to organization identifiers - Myrto Kallipoliti (OpenAIRE AMKE); Serafeim Chatzopoulos (ATHENA RC); Miriam Baglioni (CNR-ISTI); Eleni Adamidi (ATHENA RC); Paris Koloveas (ATHENA RC); Thanasis Vergoulis (ATHENA RC)

Accepted Findings Papers

  • Real-time prediction of Wikipedia articles’ quality - Carla Teixeira Lopes (University of Porto); Pedro Moás (University of Porto)
  • Human-Centred Design for Digital Ecosystems: Actors, Roles and Responsibilities - Riitta Peltonen (The National Library of Finland); Marko Nieminen (Aalto University)
  • A Comparative Analysis of Support Techniques for Assessing the Quality of Systematic Literature Reviews - Rand Alchokr (Otto von Guericke University); Athul Sunilkumar (Otto von Guericke University); Gunter Saake (Otto von Guericke University); Thomas Leich (Harz University and METOP GmbH); Jacob Krüger (Eindhoven University of Technology)
  • Citation impact and research persistence: The power of positive reinforcement - Jeppe Nicolaisen (University of Copenhagen)
  • LLM-Based Dependency Tracking for Short Event Descriptions - Naoki Sawahata (Takushoku University); Daisuke Machizawa (Takushoku University); Ryohei Ikejiri (Hiroshima University); Yasunobu Sumikawa (Takushoku University)
  • The Text+ Registry: Federating Research Data Catalogues for the Digital Humanities - Tobias Gradl (University of Bamberg); Leon Fruth (University of Bamberg); Andreas Henrich (University of Bamberg)
  • Exploring Semantic and Motion-Based Documentation for Intangible Cultural Heritage Integration - Makram Mestiri (UPHF); Meriem Khadhar (Polytechnic University of Hauts-de-France); Khalil Jedidi (Polytechnic University of Hauts-de-France); Ali S Kheyrabadi (Polytechnic University of Hauts-de-France); Zhivar Sedaghat (Polytechnic University of Hauts-de-France); Arnaud Huftier (Polytechnic University of Hauts-de-France)
  • Can LLMs Predict Citation Intent? An Experimental Analysis of In-context Learning and Fine-tuning on Open LLMs - Paris Koloveas (Athena RC); Serafeim Chatzopoulos (Athena RC); Thanasis Vergoulis (Athena RC); Christos Tryfonopoulos (University of the Peloponnese)
  • What Makes a User Click on a News Item? Understanding News Values of Visual Content in News Recommendation - Bruno N. Sotic (University of Amsterdam); Jaap Kamps (University of Amsterdam)
  • Blowin' in the Wind: The Challenges of Archiving Social Media for Digital Humanities Research - George Buchanan (RMIT University); Dana McKay (RMIT University)
  • SciTableQA: A Question-Answering Benchmark for Complex Scientific Tables - Kehinde Ajayi (Old Dominion University); Yi He (William & Mary University); Jian Wu (Old Dominion University); Kris SeekFord (Old Dominion University); Matthew Maisonave (Old Dominion University)

Accepted Short Papers

  • NERGL: Named Entity Recognition and Grounding with Large Language Models for Ukiyo-e Artworks - Bohao Wu (Ritsumeikan University); Akira Maeda (Ritsumeikan University)
  • A Study of Temporal Fusion Strategies for Named Entity Recognition in Historical Texts - Emanuela Boros (EPFL)
  • Cite Lens: An AI Tool for Detecting Out-of-Scope and Out-of-Context Citations - Jean-Baptiste de la Broise (MDPI); Frank Sauerburger (MDPI); Enric Sayas (MDPI); Dan-Marin Tecu (MDPI); Sanita Meijere (MDPI); Milos Cuculovic (MDPI)
  • Information Specialists’ Perspectives on Research Data Management Support in Social Sciences and Humanities - Anna Sendra Toset (Tampere University); Minna Ahokas (CSC – IT Center for Science); Sanna Kumpulainen (Tampere University)
  • StoryNetworks: An Annotated Dataset of Event Dependencies from Short Descriptions - Daisuke Machizawa (Takushoku University); Naoki Sawahata (Takushoku University); Ryohei Ikejiri (Hiroshima University); Yasunobu Sumikawa (Takushoku University)
  • Evaluating Human-LLM Alignment in ETD Subject Classification - Hajra Klair (Virginia Tech); Fausto German (Virginia Tech); Bipasha Banerjee (Virginia Tech); William Ingram (Virginia Tech)
  • Linking References to Documents in Parliamentary Debates - Floris Bos (IRlab, Informatics Institute, University of Amsterdam); Marc van Opijnen (Publications Office of the Netherlands (Logius|Koop)); Maarten Marx (IRlab, Informatics Institute, University of Amsterdam)
  • From notes to models: Leveraging LLMs for museum closure data - George Wright (King's College London); Andrea Ballatore (King's College London); Alexandra Poulovassilis (Birkbeck, University of London); Peter Wood (Birkbeck, University of London)
  • LLM-Based Information Extraction to Support Scientific Literature Research and Publication Workflows - Samy Ateia (University of Regensburg); Udo Kruschwitz (University of Regensburg); Melanie Scholz (University of Bayreuth); Moayad Almohaishi (University of Bayreuth); Agnes Koschmider (University of Bayreuth)
  • Using LLMs for Improving the OCR Accuracy of Old Greek Handwritten Documents - Andreas Evangelatos (National Centre for Scientific Research "Demokritos"); Konstantinos Palaiologos (National Centre for Scientific Research "Demokritos"); Basilis Gatos (National Centre for Scientific Research "Demokritos"); Panagiotis Kaddas (National Centre for Scientific Research "Demokritos"); Aikaterini Christopoulou (National Centre for Scientific Research "Demokritos"); Vassilis Katsouros (Institute for Language and Speech Processing & Archimedes, Athena Research Center, Greece); Andreas Kakridis (Bank of Greece & Panteion University, Athens)
  • Is Word2Vec Dead for Topic Modeling? A Case Study on Hospitality Opinion Mining Says No - Marc-Alexis Azais (L3i); Mickael Coustaty (La Rochelle University - L3i); Jean-Loup Guillaume (La Rochelle University - L3i)
  • DM-LP: A Large Arabic script languages Dataset for OCR and Cataloguing Research - Luca Sala (University of Modena and Reggio Emilia); Riccardo Amerigo Vigliermo (Fondazione per le Scienze Religiose); Giovanni Sullutrone (University of Modena and Reggio Emilia); Sonia Bergamaschi (University of Modena and Reggio Emilia)
  • Sharing is Caring: A Text Alignment Approach for Sharing Annotations of Copyrighted Texts - Frederik Arnold (Humboldt-Universität zu Berlin); Robert Jäschke (Humboldt-Universität zu Berlin)
  • Tracing the Evolution of Coastal Scientific Literature in Scopus (1970-2023) - Julien Delaunay (L3i / LIENSs, University of La Rochelle); Marc-Alexis Azaïs (L3i); Dipendra Sharma Kafle (L3i); Nicolas Sidere (L3i); Antoine Doucet (L3i); Olivier de Viron (LIENSs)
  • On Recommending Fair Influential Scholars with Geographically Diverse Impact - Arpan Dam (IIT Kharagpur); Sayan Pathak (Microsoft AI and Research); Bivas Mitra (IIT Kharagpur)
  • Ranking To Learn: Human Experts, Search Engines, or LLMs for Learning Guidance - Yasin Ghafourian Boroojerdnia (Research Studios Austria Forschungsgesellschaft); Allan Hanbury (Technische Universität Wien (TU Wien)); Petr Knoth (Knowledge Media Institute, The Open University)
  • WCAG compliance of open government documents - Gregory Slager (IRlab, Informatics Institute, University of Amsterdam); Maarten Marx (IRlab, Informatics Institute, University of Amsterdam)
  • Semantic Enrichment in SQL Workflows through Targeted LLM Invocation - Yannis Foufoulas (Athena Research Center); Eleni Zacharia (OpenAIRE AMKE); Harry Dimitropoulos (OpenAIRE AMKE); Natalia Manola (OpenAIRE AMKE); Yannis Ioannidis (University of Athens)
  • Design and Implementation of a Next-Generation OAIS-Compliant Digital Preservation System for the NDPP - Lu Wang (National Science Library, Chinese Academy of Sciences); Beibei Kong (National Science Library, Chinese Academy of Sciences); Zhenxin Wu (National Science Library, Chinese Academy of Sciences)
  • Identification of potential Co-citation Linkages via Context-aware Citation Network Embeddings - Masaki Eto (Gakushuin Women's College)

Accepted Demos

  • Drawio2Triples: Semantic Validation and RDF Transformation of CIDOC CRM Example Diagrams - Elias Tzortzakakis (FORTH-ICS); Pavlos Fafalios (FORTH-ICS)
  • Interactive Association Map Creation from Documents using Association Rule Mining - Efthimios Mitkousis (Computer Science Department, University of Crete); Yannis Tzitzikas (FORTH-ICS and Computer Science Department, University of Crete)
  • Interactive and Provenance-aware Search and QA over Documents using LLMs, RAG and Knowledge Graph Verbalization - Iordanis Sapidis (Institute of Computer Science - FORTH, Greece, and Computer Science Department - University of Crete, Greece); Valantis Zervos (Institute of Computer Science - FORTH, Greece, and Computer Science Department - University of Crete, Greece); Michalis Mountantonakis (Institute of Computer Science - FORTH, Greece, and Computer Science Department - University of Crete, Greece); Yannis Tzitzikas (Institute of Computer Science - FORTH, Greece, and Computer Science Department - University of Crete, Greece)
  • Demonstrating Narrative Pattern Discovery from Biomedical Literature - Hermann Kroll (TU Braunschweig); Pascal Sackhoff (TU Braunschweig); Bill Matthias Thang (TU Braunschweig); Christin Katharina Kreutz (TH Mittelhessen / Herder Institut); Wolf-Tilo Balke (TU Braunschweig)
  • A Modern Open Source Integrated Library System by Invenio - Karolina Przerwa (CERN); Salome Rohr (CERN)
  • IILAP: Interactive Information Literacy Assessment Platform - Liana Ermakova (Université de Bretagne Occidentale); Petra Dadic (Université de Bretagne Occidentale)
  • Mass migration of records: LRM-Factory, a solution to facilitate the transition to Linked Data for bibliographic agencies - Marie Bastien (HCL); Morgane Sedoud (HCL)
  • LLM-Enhanced DETEXA Workflow Builder for Semantic Enrichment - Yannis Foufoulas (Athena Research Center); Eleni Zacharia (OpenAIRE AMKE); Harry Dimitropoulos (OpenAIRE AMKE); Natalia Manola (OpenAIRE AMKE); Yannis Ioannidis (University of Athens)