Co-Designing a Knowledge Graph Navigation Interface: A Participatory Approach
Stanislava Gardasevic, Manika Lamba, Jasmine S. Malone
TL;DR
The paper tackles the problem of navigating multilayered knowledge graphs by deriving actionable, user-centered interface guidelines from a participatory design workshop with PhD students. It extends prior work through an iterative design process that translates end-user needs into a prototype interface emphasizing recommendations, profiles, predefined queries, and knowledge cards to reduce visual complexity. The study contributes a coherent framework for knowledge-graph navigation in educational domains and demonstrates how participatory design can yield innovative, user-centric visualization solutions; it also outlines future integration with GraphRAG to enable AI-augmented graph population and querying. The practical impact lies in producing design-oriented guidance that can improve the usability and adoption of knowledge-graph tools in academic settings and similar domains, with a path toward scalable, transparent AI-assisted graph exploration.
Abstract
Navigating and visualizing multilayered knowledge graphs remains a challenging, unresolved problem in information systems design. Building on our earlier study, which engaged end users in both the design and population of a domain-specific knowledge graph, we now focus on translating their insights into actionable interface guidelines. In this paper, we synthesize recommendations drawn from a participatory workshop with doctoral students. We then demonstrate how these recommendations inform the design of a prototype interface. Finally, we found that a participatory iterative design approach can help designers in decision making, leading to interfaces that are both innovative and user-centric. By combining user-driven requirements with proven visualization techniques, this paper presents a coherent framework for guiding future development of knowledge-graph navigation tools.