Natural Language Interaction for Editing Visual Knowledge Graphs

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Shahriari, Reza, Ragan, Eric D., Ruiz, Jaime
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917142534815744
author Shahriari, Reza
Ragan, Eric D.
Ruiz, Jaime
author_facet Shahriari, Reza
Ragan, Eric D.
Ruiz, Jaime
contents Knowledge graphs are often visualized using node-link diagrams that reveal relationships and structure. In many applications using graphs, it is desirable to allow users to edit graphs to ensure data accuracy or provides updates. Commonly in graph visualization, users can interact directly with the visual elements by clicking and typing updates to specific items through traditional interaction methods in the graphical user interface. However, it can become tedious to make many updates due to the need to individually select and change numerous items in a graph. Our research investigates natural language input as an alternative method for editing network graphs. We present a user study comparing GUI graph editing with two natural language alternatives to contribute novel empirical data of the trade-offs of the different interaction methods. The findings show natural language methods to be significantly more effective than traditional GUI interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2512_11674
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Natural Language Interaction for Editing Visual Knowledge Graphs
Shahriari, Reza
Ragan, Eric D.
Ruiz, Jaime
Human-Computer Interaction
Knowledge graphs are often visualized using node-link diagrams that reveal relationships and structure. In many applications using graphs, it is desirable to allow users to edit graphs to ensure data accuracy or provides updates. Commonly in graph visualization, users can interact directly with the visual elements by clicking and typing updates to specific items through traditional interaction methods in the graphical user interface. However, it can become tedious to make many updates due to the need to individually select and change numerous items in a graph. Our research investigates natural language input as an alternative method for editing network graphs. We present a user study comparing GUI graph editing with two natural language alternatives to contribute novel empirical data of the trade-offs of the different interaction methods. The findings show natural language methods to be significantly more effective than traditional GUI interaction.
title Natural Language Interaction for Editing Visual Knowledge Graphs
topic Human-Computer Interaction
url https://arxiv.org/abs/2512.11674