Related Experiment Video
Updated: Jul 1, 2026

07:09
Virtual Reality Experiments with Physiological Measures
Published on: August 29, 2018
Graph-based analysis of work-from-home layouts and affective responses in virtual reality
1Department of Architecture, Joongbu University, Goyang, Republic of Korea.
Scientific Reports
|June 29, 2026
Summary
This study uses graph-based learning in virtual reality to model how work-from-home furniture layouts affect user feelings. It found that spatial relationships, like desk placement, significantly influence user experience and workspace perception.
Area of Science:
- Human-Computer Interaction
- Computational Social Science
- Environmental Psychology
Background:
- Understanding the link between physical workspace design and user well-being is crucial for effective work-from-home (WFH) environments.
- Traditional methods struggle to capture complex spatial relationships in interior design.
- Virtual reality (VR) offers a controlled environment to study user responses to various layouts.
Purpose of the Study:
- To develop and evaluate a graph-based learning framework for modeling associations between WFH furniture layouts and user affective responses.
- To investigate the impact of spatial relationships between furniture and architectural elements on user experience in VR.
- To demonstrate the methodological advantages of graph representations for analyzing interior space-user interaction.
Main Methods:
- A graph-based learning framework using GraphSAGE with attention pooling was developed to predict user affective responses.
- Eighty-five work-from-home (WFH) furniture layouts were created and evaluated by 43 participants in a virtual reality (VR) environment.
- Layouts were represented as spatial graphs, with furniture and architectural elements as nodes and proximity as edges, and rated on six outcomes.
Main Results:
- The graph-based model achieved a mean absolute error of 0.684 and a variance-weighted R² of approximately 0.659 in predicting user responses.
- The graph model outperformed non-graph baseline models in prediction accuracy for this dataset.
- GNNExplainer identified key influential subgraphs, particularly desk-related spatial configurations (e.g., desk-window, desk-door).
Conclusions:
- Graph-based representation provides a valuable methodological approach for evaluating the association between object-level spatial relationships in WFH layouts and user experience.
- The study highlights the importance of specific furniture arrangements and their proximity to architectural features in shaping user perception and satisfaction.
- This framework offers a novel way to analyze and optimize interior spatial designs for improved user affective responses.
Related Concept Videos
Virtual Work
The principle of virtual work states that if a body is in static and dynamic equilibrium, then the sum of all the virtual work done by all external forces and couple moments for any given virtual displacement must be zero.
In static equilibrium, a body can experience an imaginary or virtual movement, such as displacement or rotation. The virtual work done by a force is equal to the dot product of force and virtual displacement in the direction of the force. When it comes to virtually rotating a...
In static equilibrium, a body can experience an imaginary or virtual movement, such as displacement or rotation. The virtual work done by a force is equal to the dot product of force and virtual displacement in the direction of the force. When it comes to virtually rotating a...
Virtual Work for a System of Connected Rigid Bodies
Virtual work is a powerful method used to solve problems involving several connected rigid bodies. When the system is in equilibrium, virtual work is zero. This allows the calculation of the resulting forces when a system undergoes a virtual displacement. When attempting to analyze such a system, first, use a free-body diagram, where an independent coordinate represents the configuration of the links, and mark its deflected position resulting from the positive virtual displacement.
Next,...
Next,...
