Knowledge Graphs in Cultural Heritage

Abstract
Knowledge Graphs (KGs) are emerging as powerful tools for cultural heritage (CH) applications, offering a structured and interconnected way to represent vast and diverse information about artifacts, historical events, creators, and more. As KGs transform disparate, siloed, CH artifacts into a rich, navigable web of entities and relationships, allow at the same time for more intelligent search, discovery, and analysis, moving beyond keyword matching to understanding the underlying meaning and connections within CH collections. KGs facilitate the integration of heterogeneous sources of cultural data, from museum inventories and archival documents to archaeological findings and expert annotations, creating a unified knowledge base that can support various user groups, including researchers, curators, and the general public.
Despite previous and ongoing research work in the use of KGs in CH there are still significant research challenges, as CH research encompasses a multitude of disciplines from the humanities and social sciences (e.g. archaeology, cultural anthropology, history and art history), to natural sciences (e.g. biology, chemistry, physics) and exact sciences (e.g. mathematics, computer and data sciences), each with their own distinct methodologies and workflows. The first important one stems from the heterogeneity and fragmentation of data. CH data is notoriously diverse in format, quality, and granularity, ranging from structured databases to unstructured texts and multimedia. Integrating this disparate information into a coherent graph requires robust methodologies for data harmonization, entity resolution, and schema alignment. Another challenge is the inherent ambiguity and subjectivity within CH knowledge. Historical interpretations can vary, and provenance information is often incomplete or uncertain. KGs need to be able to represent and manage this uncertainty, perhaps through probabilistic links or by incorporating multiple perspectives. Furthermore, scalability and maintainability are crucial concerns. And as usual user interaction and visualization remain active research areas. Especially, the ability to add query-to-text interfaces through various AI LLMs emerges as an important aspect for the uptake of the use of KGs in CH applications.
But integrating AI with KGs introduces further complexities. A key concern is bias amplification: as AI models get trained on historical data, they can perpetuate societal biases, leading to skewed interpretations. This requires careful data curation and explainable AI (XAI) solutions so as to ensure fairness. The interpretability of AI-driven insights is another challenge; "black box" AI systems hinder understanding of their rationale, clashing with CH's emphasis on provenance and human validation. Interesting questions arise on how we can use KGs to tackle these issues of bias and transparency in the CH domain. Extending these questions to tackle issues of AI generated CH content or authenticity of CH artifacts, could provide additional roles for the use of cultural KGs.
The workshop aims at exploring problems and solutions in this area and leverage existing efforts in the European and international level like the projects ECHOES (EU) and RICHES (UK) and explore how emerging CH infrastructures can benefit from the advanced use of KGs.

Topics of interest

• Knowledge Graphs and Cultural Heritage Applications
• AI and Knowledge Graphs in Cultural Heritage
• Transformation of CH knowledge from/to KGs
• Ontologies for CH and KGs
• Cultural Data Integration through Knowledge Graphs
• Bias in Knowledge Graphs
• Interpretability through KGs in CH

Organizers

• Dimitris Kotzinos
  Dimitris Kotzinos is a Full Professor at the Department of Computer Science of the CY Cergy Paris University, member of the ETIS Lab and member of the MIDI team of the lab. He holds a Ph.D. in Computer Science (in Real-Time Web Information Systems) (2001) and a M.Sc. in Transportation (1996), where he studied networks and their applications in transportation systems. His main research interests include data management algorithms, techniques and tools; development of methodologies, algorithms and tools for web-based information systems, portals and web services; and the understanding of the meaning (semantics) of interoperable data and services on the web. Recently he has started working on studying the formation and evolution of discussions in online social networks using Machine Learning (ML) and Artificial Intelligence (AI) techniques. Additionally, he is working in accountability, explainability and fairness of the ML and AI algorithms, especially when applied in data engineering and analysis problems; this includes issues on data privacy and especially their intersection with the publication of Linked Open Data. Dimitris is participating in ECHOES, a flagship EU-funded project that aims to build the European Collaborative Cloud for Cultural Heritage. Dimitris has published more than 80 articles in various journals, books, conferences and workshops and serves as a program committee member and reviewer for various conferences and journals. He is also participating in nationally and internationally funded research programs around data analytics, data models and networks and their integration in the everyday life.
• Sorin Hermon
  Sorin Hermon is associate professor at The Cyprus Institute. His research is situated within two converging fields: Digital Cultural Heritage and Heritage Science, developing computer graphics and computer vision-based methods for the shape analysis of artefacts, works of art, archaeological features or buildings in order to characterize their form, materiality, production techniques, technologies of manufacture and their state of conservation, from macro to nano-scale; integrating hyper-spectral and technical imaging data with 3D documentation, and defining formal knowledge representation structures, including domain ontologies, their associated knowledge graphs and related digital repositories. He applies these methodologies on current grant challenges of Cultural Heritage (CH), namely developing sustainable disaster risk and management strategies for reducing the impact of Climate Change on CH, combatting the illicit trafficking of cultural goods and developing open-science workflows for the research-conservation-valorization of CH. Sorin has published more than 120 peer-reviewed research papers, supervised several PhD and MSc students and is director of the MSc program in Digital Cultural Heritage at The Cyprus Institute. He is a member of the Steering Committee of ECHOES, the EU funded project aimed at developing and implementing the European Collaborative Cloud for Cultural Heritage, being responsible, among others, to frame the concept of Heritage Digital Twins as digital commons and to ensure their digital continuum.
• Maria Theodoridou
  Maria Theodoridou is Research & Development Engineer at the Foundation for Research and Technology – Hellas, Institute of Computer Science (FORTH-ICS), Information Systems Laboratory and the Centre for Cultural Informatics (CCI). She holds a Master of Applied Science in Electrical & Computer Engineering from the University of Toronto, Canada (1985) and a Diploma in Electrical Engineering from the Aristotle University of Thessaloniki, Greece (1983). Maria has been actively involved in more than 20 national and international cultural information systems' projects. Her research interests include semantic web technologies, mapping technologies, conceptual modelling, cultural information systems and semantic interoperability. Currently, she coordinates the mapping technology activities of CCI that include the X3ML Toolkit a set of small, open source, microservices that assist the data provisioning and aggregation process for information integration, extensively used for mapping and transforming data from cultural heritage institutions, such as archives, libraries, and museums, but equally for research institutes of descriptive sciences such as earth sciences, biodiversity, clinical studies and e-Health. Maria was the technical/scientific coordinator of FORTH-ICS in several recent EU projects (ARIADNEplus, 4CH, E-RIHS, ITN-DCH, ARIADNE, PARTHENOS, VRE4EIC). She is currently the scientific coordinator of FORTH-ICS for the EU ECCCH Project ECHOES.

Call for Papers
The workshop invites scholars and R&D experts in related fields to submit papers with unpublished results. Authors must prepare their papers following Springer's Instructions for Authors of Proceedings. The maximum length for submissions is 15 pages. Papers will be submitted in PDF format using EasyChair: https://easychair.org/conferences/?conf=ijckg2025 (make sure to select the track with name "Workshop "Knowledge Graphs in Cultural Heritage")

Important Dates

• Paper Submissions: June 30, 2025 (11:59 PM AoE)
• Notification of Acceptance: July 15, 2025 (11:59 PM AoE)
• Camera Ready Submissions: August 1, 2025 (11:59 PM AoE)
• Workshop Date: October 15-17, 2025 (duration: half a day - to be anounced)