Supporting Visual Analytics System Authoring Through Knowledge Graph Representations of Design Studies

The development of visual analytics systems often relies on design study methodologies that organize collaboration between domain experts and visualization researchers across multiple stages. Despite their merit, these studies often encounter recurring deficiencies that undermine both the efficiency of the study and the long-term value of the resulting systems. Although retrospective and reflective reports are considered thorough documentation of final outcomes, far less attention is given to capturing the reasoning behind key decisions and the knowledge generated through expert interactions during the study itself. In this work, we address this gap by introducing a methodology for capturing and analyzing these design studies, grounded in three real-world urban visual analytics projects that provide concrete insight into how capturing knowledge of collaborative authoring among various stakeholders can be important in practice. We employ large language models to convert unstructured interaction logs and expert annotations into a semantically rich, multimodal knowledge graph that represents collaborative authoring processes in visual analytics systems. This representation supports structured knowledge extraction, interactive exploration, and systematic analysis of expert interactions, helping reveal and mitigate recurring weaknesses in traditional design study workflows.

Author dc:creator

• Vamsi Dath Meka (24400169)

• Computer Science

Statement dc:rights

• In Copyright
• Open Access after 2028-05-01

DOI dc:identifier

https://doi.org/10.25417/uic.32995226.v1

OAI identifier oai:identifier

oai:figshare.com:article/32995226