Artificial Curators - Design Considerations for Interactive Chatbot Experiences in Cultural Heritage Settings

Journal Article (2026)
Author(s)

J.S. Love (TU Delft - Industrial Design Engineering)

Eric Heng Gu (TU Delft - Industrial Design Engineering)

Jeroen Vandommele (National Library of the Netherlands)

Research Group
Knowledge and Intelligence Design
URL related publication
https://www.digitalcultureandeducation.com/volume-163
More Info
expand_more
Publication Year
2026
Language
English
Research Group
Knowledge and Intelligence Design
Journal title
Digital Culture and Education
Issue number
3
Volume number
16
Pages (from-to)
6-40
Page Views
53
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This paper explores the design and implementation of CuratorBot, an interactive chatbot developed to enhance visitor engagement in cultural heritage institutions using generative large language models. Positioned as a conversational guide, CuratorBot simulates a docent's role of enabling personalised, dynamic dialogues about historical artefacts, specifically focusing on the Dutch National Library's Visboeck manuscript. CuratorBot offers visitors the opportunity to actively interact with cultural heritage by having a conversation with a computer partner.
Through iterative design experiments, user interaction observations and surveys, we assess the chatbot's capacity to foster curiosity, support free-choice learning and facilitate human-like conversations, thereby making cultural experiences more accessible and engaging for a broader audience. The development process involved continuous user feedback which highlighted key areas of improvement and adaptation to better serve visitor needs. The paper addresses opportunities and challenges of using LLM-based conversational agents in heritage settings and offers insights for future development of visitor engagement tools with embedded machine learning. We also discuss broader implications of incorporating generative conversational interfaces in GLAMs by examining how such tools can contribute to the
evolving landscape of digital cultural heritage.