Towards Modeling Visualization Processes as Dynamic Bayesian Networks | IEEE Journals & Magazine | IEEE Xplore
Scheduled Maintenance: On Tuesday, 25 February, IEEE Xplore will undergo scheduled maintenance from 1:00-5:00 PM ET (1800-2200 UTC). During this time, there may be intermittent impact on performance. We apologize for any inconvenience.

Towards Modeling Visualization Processes as Dynamic Bayesian Networks


Abstract:

Visualization designs typically need to be evaluated with user studies, because their suitability for a particular task is hard to predict. What the field of visualizatio...Show More

Abstract:

Visualization designs typically need to be evaluated with user studies, because their suitability for a particular task is hard to predict. What the field of visualization is currently lacking are theories and models that can be used to explain why certain designs work and others do not. This paper outlines a general framework for modeling visualization processes that can serve as the first step towards such a theory. It surveys related research in mathematical and computational psychology and argues for the use of dynamic Bayesian networks to describe these time-dependent, probabilistic processes. It is discussed how these models could be used to aid in design evaluation. The development of concrete models will be a long process. Thus, the paper outlines a research program sketching how to develop prototypes and their extensions from existing models, controlled experiments, and observational studies.
Published in: IEEE Transactions on Visualization and Computer Graphics ( Volume: 27, Issue: 2, February 2021)
Page(s): 1000 - 1010
Date of Publication: 19 October 2020

ISSN Information:

PubMed ID: 33074817

References

References is not available for this document.