Towards a visual guide for communicating uncertainty in Visual Analytics

Karsten Seipp, Francisco Gutiérrez, Xavier Ochoa, Katrien Verbert

Research output: Contribution to journalArticle

Abstract

This article presents a first step towards the definition of a visual guide for communicating uncertainty which is to fit into existing visualisation frameworks and toolkits. The first entry in our guide is made by a set of visual variables appropriate for representing areal uncertainty in algorithm mechanics. Such visualisations show users how data points are distributed in the classification space and allow them to understand the “goodness-of-fit” of their data to the algorithm. This is important for Visual Analytics applications, which combine Information Visualisation with information mining techniques in an interactive decision-making process. Model uncertainties stemming from widely spread data points need to be visualised so that the user can make adjustments and improve the analysis. To capitalise on established knowledge and meaning, we explore whether popular visual variables for representing areal uncertainty in the domain of geospatial visualisation may also be effective for representing uncertainty in the visualisation of the mechanics of K-means clustering and Linear Regression algorithms, as both use a spatial distribution of data points. In a study with 500 participants we find that overall the visual means opacity performs best, followed by texture, but that grid and blur may be unsuitable for quantifying uncertainty. The performance of contour lines appears to depend on the algorithm visualisation. Using this study, we extend the validity of a set of domain-specific findings from geospatial visualisation to the visualisation of algorithm mechanics and use these to form the first building blocks of a cross-disciplinary visual guide for representing uncertainty, laying promising foundations for future work.

Original languageEnglish (US)
Pages (from-to)1-18
Number of pages18
JournalJournal of Visual Languages and Computing
Volume50
DOIs
StatePublished - Feb 1 2019

Fingerprint

Visualization
Mechanics
Uncertainty
Opacity
Linear regression
Spatial distribution
Textures
Decision making
Datum Point

Keywords

  • Algorithm mechanics
  • Geospatial visualisation
  • Information Visualisation
  • Laymen
  • Non-experts
  • Uncertainty representation
  • Visual Analytics
  • Visual language

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Towards a visual guide for communicating uncertainty in Visual Analytics. / Seipp, Karsten; Gutiérrez, Francisco; Ochoa, Xavier; Verbert, Katrien.

In: Journal of Visual Languages and Computing, Vol. 50, 01.02.2019, p. 1-18.

Research output: Contribution to journalArticle

Seipp, Karsten ; Gutiérrez, Francisco ; Ochoa, Xavier ; Verbert, Katrien. / Towards a visual guide for communicating uncertainty in Visual Analytics. In: Journal of Visual Languages and Computing. 2019 ; Vol. 50. pp. 1-18.
@article{636a022df3b84d4d86b1e235d1e649c3,
title = "Towards a visual guide for communicating uncertainty in Visual Analytics",
abstract = "This article presents a first step towards the definition of a visual guide for communicating uncertainty which is to fit into existing visualisation frameworks and toolkits. The first entry in our guide is made by a set of visual variables appropriate for representing areal uncertainty in algorithm mechanics. Such visualisations show users how data points are distributed in the classification space and allow them to understand the “goodness-of-fit” of their data to the algorithm. This is important for Visual Analytics applications, which combine Information Visualisation with information mining techniques in an interactive decision-making process. Model uncertainties stemming from widely spread data points need to be visualised so that the user can make adjustments and improve the analysis. To capitalise on established knowledge and meaning, we explore whether popular visual variables for representing areal uncertainty in the domain of geospatial visualisation may also be effective for representing uncertainty in the visualisation of the mechanics of K-means clustering and Linear Regression algorithms, as both use a spatial distribution of data points. In a study with 500 participants we find that overall the visual means opacity performs best, followed by texture, but that grid and blur may be unsuitable for quantifying uncertainty. The performance of contour lines appears to depend on the algorithm visualisation. Using this study, we extend the validity of a set of domain-specific findings from geospatial visualisation to the visualisation of algorithm mechanics and use these to form the first building blocks of a cross-disciplinary visual guide for representing uncertainty, laying promising foundations for future work.",
keywords = "Algorithm mechanics, Geospatial visualisation, Information Visualisation, Laymen, Non-experts, Uncertainty representation, Visual Analytics, Visual language",
author = "Karsten Seipp and Francisco Guti{\'e}rrez and Xavier Ochoa and Katrien Verbert",
year = "2019",
month = "2",
day = "1",
doi = "10.1016/j.jvlc.2018.11.004",
language = "English (US)",
volume = "50",
pages = "1--18",
journal = "Journal of Visual Languages and Computing",
issn = "1045-926X",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Towards a visual guide for communicating uncertainty in Visual Analytics

AU - Seipp, Karsten

AU - Gutiérrez, Francisco

AU - Ochoa, Xavier

AU - Verbert, Katrien

PY - 2019/2/1

Y1 - 2019/2/1

N2 - This article presents a first step towards the definition of a visual guide for communicating uncertainty which is to fit into existing visualisation frameworks and toolkits. The first entry in our guide is made by a set of visual variables appropriate for representing areal uncertainty in algorithm mechanics. Such visualisations show users how data points are distributed in the classification space and allow them to understand the “goodness-of-fit” of their data to the algorithm. This is important for Visual Analytics applications, which combine Information Visualisation with information mining techniques in an interactive decision-making process. Model uncertainties stemming from widely spread data points need to be visualised so that the user can make adjustments and improve the analysis. To capitalise on established knowledge and meaning, we explore whether popular visual variables for representing areal uncertainty in the domain of geospatial visualisation may also be effective for representing uncertainty in the visualisation of the mechanics of K-means clustering and Linear Regression algorithms, as both use a spatial distribution of data points. In a study with 500 participants we find that overall the visual means opacity performs best, followed by texture, but that grid and blur may be unsuitable for quantifying uncertainty. The performance of contour lines appears to depend on the algorithm visualisation. Using this study, we extend the validity of a set of domain-specific findings from geospatial visualisation to the visualisation of algorithm mechanics and use these to form the first building blocks of a cross-disciplinary visual guide for representing uncertainty, laying promising foundations for future work.

AB - This article presents a first step towards the definition of a visual guide for communicating uncertainty which is to fit into existing visualisation frameworks and toolkits. The first entry in our guide is made by a set of visual variables appropriate for representing areal uncertainty in algorithm mechanics. Such visualisations show users how data points are distributed in the classification space and allow them to understand the “goodness-of-fit” of their data to the algorithm. This is important for Visual Analytics applications, which combine Information Visualisation with information mining techniques in an interactive decision-making process. Model uncertainties stemming from widely spread data points need to be visualised so that the user can make adjustments and improve the analysis. To capitalise on established knowledge and meaning, we explore whether popular visual variables for representing areal uncertainty in the domain of geospatial visualisation may also be effective for representing uncertainty in the visualisation of the mechanics of K-means clustering and Linear Regression algorithms, as both use a spatial distribution of data points. In a study with 500 participants we find that overall the visual means opacity performs best, followed by texture, but that grid and blur may be unsuitable for quantifying uncertainty. The performance of contour lines appears to depend on the algorithm visualisation. Using this study, we extend the validity of a set of domain-specific findings from geospatial visualisation to the visualisation of algorithm mechanics and use these to form the first building blocks of a cross-disciplinary visual guide for representing uncertainty, laying promising foundations for future work.

KW - Algorithm mechanics

KW - Geospatial visualisation

KW - Information Visualisation

KW - Laymen

KW - Non-experts

KW - Uncertainty representation

KW - Visual Analytics

KW - Visual language

UR - http://www.scopus.com/inward/record.url?scp=85057731604&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057731604&partnerID=8YFLogxK

U2 - 10.1016/j.jvlc.2018.11.004

DO - 10.1016/j.jvlc.2018.11.004

M3 - Article

AN - SCOPUS:85057731604

VL - 50

SP - 1

EP - 18

JO - Journal of Visual Languages and Computing

JF - Journal of Visual Languages and Computing

SN - 1045-926X

ER -