NEXO: Adaptive Visualization for Comparative Exploration of Knowledge Graphs with Natural Language Interaction
Authors
Reza Shahriari (University of Florida), Justin Whorton (University of Arkansas for Medical Sciences (UAMS)), Jonathan Bona (University of Arkansas for Medical Sciences (UAMS)), Kevin Sexton (Vanderbilt University Medical Center), Mathias Brochhausen (University of Arkansas for Medical Sciences (UAMS)), Jaime Ruiz (University of Florida), Eric Ragan (University of Florida)
Presentation
- Session
- Talk to my agent
- Time
- Tuesday, Nov 10, 11:12 – 11:24 (US/Eastern) · session 10:00 – 11:30
- Location
- Hall Essex center
Keywords
Knowledge Graph, Graph Visualization, Natural Language Interaction, Human-in-the-Loop
Abstract
Knowledge graphs (KGs) capture rich, multi-relational data, but comparing entities, relationships, and local structures remains challenging with traditional graph visualizations. We present NEXO, a task-driven system for comparative KG exploration that combines natural language interaction with adaptive, coordinated visualizations. The system translates free-form queries into structured comparison tasks and supports value comparison, path comparison, and neighborhood exploration across one-to-one, one-to-many, and many-to-many comparison structures. Rather than exposing users to the full graph, NEXO generates task-specific views that combine structural context with concise summaries to support efficient comparison.We evaluate the system through a user study with eye tracking to assess task performance and attention allocation across coordinated views. Participants completed tasks with high accuracy and minimal query reformulation. Gaze patterns reveal task-dependent attention strategies, with users relying more on graph views for structural exploration and summary views for pattern identification and comparison. These findings demonstrate the effectiveness of combining natural language interaction with task-adaptive visualizations for comparative KG exploration.
For Practitioners
Practitioners who work with knowledge graphs and graph databases, including data scientists, biomedical informaticians, digital librarians, cybersecurity analysts, enterprise knowledge management professionals, and software engineers developing graph-based applications would be interested in this work. Researchers and practitioners in domains such as healthcare, scientific literature analysis, and business intelligence, where large knowledge graphs are commonly used, can also benefit from the proposed approach. The paper also provides practical design guidance for combining natural language interaction with adaptive coordinated visualizations, transparent parameter editing, and comparison-focused visual summaries. These principles can help developers build more accessible and efficient graph exploration tools that support tasks such as comparing entities, relationships, and local graph structures while reducing the complexity of navigating large knowledge graphs.