Guidance in the human–machine analytics process

Christopher Collins, Natalia Andrienko, Tobias Schreck, Jing Yang, Jaegul Choo, Ulrich Engelke, Amit Jena, Tim Dwyer

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we list the goals for and the pros and cons of guidance, and we discuss the role that it can play not only in key low-level visualization tasks but also the more sophisticated model-generation tasks of visual analytics. Recent advances in artificial intelligence, particularly in machine learning, have led to high hopes regarding the possibilities of using automatic techniques to perform some of the tasks that are currently done manually using visualization by data analysts. However, visual analytics remains a complex activity, combining many different subtasks. Some of these tasks are relatively low-level, and it is clear how automation could play a role—for example, classification and clustering of data. Other tasks are much more abstract and require significant human creativity, for example, linking insights gleaned from a variety of disparate and heterogeneous data artifacts to build support for decision making. In this paper, we outline the potential applications of guidance, as well as the inputs to guidance. We discuss challenges in implementing guidance, including the inputs to guidance systems and how to provide guidance to users. We propose potential methods for evaluating the quality of guidance at different phases in the analytic process and introduce the potential negative effects of guidance as a source of bias in analytic decision making.

Original languageEnglish
Pages (from-to)166-180
Number of pages15
JournalVisual Informatics
Volume2
Issue number3
DOIs
Publication statusPublished - 2018 Sep 1

Fingerprint

Visualization
Decision making
Artificial intelligence
Learning systems
Automation

Keywords

  • Guidance
  • Model evaluation
  • Visual analytics

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Collins, C., Andrienko, N., Schreck, T., Yang, J., Choo, J., Engelke, U., ... Dwyer, T. (2018). Guidance in the human–machine analytics process. Visual Informatics, 2(3), 166-180. https://doi.org/10.1016/j.visinf.2018.09.003

Guidance in the human–machine analytics process. / Collins, Christopher; Andrienko, Natalia; Schreck, Tobias; Yang, Jing; Choo, Jaegul; Engelke, Ulrich; Jena, Amit; Dwyer, Tim.

In: Visual Informatics, Vol. 2, No. 3, 01.09.2018, p. 166-180.

Research output: Contribution to journalArticle

Collins, C, Andrienko, N, Schreck, T, Yang, J, Choo, J, Engelke, U, Jena, A & Dwyer, T 2018, 'Guidance in the human–machine analytics process', Visual Informatics, vol. 2, no. 3, pp. 166-180. https://doi.org/10.1016/j.visinf.2018.09.003
Collins C, Andrienko N, Schreck T, Yang J, Choo J, Engelke U et al. Guidance in the human–machine analytics process. Visual Informatics. 2018 Sep 1;2(3):166-180. https://doi.org/10.1016/j.visinf.2018.09.003
Collins, Christopher ; Andrienko, Natalia ; Schreck, Tobias ; Yang, Jing ; Choo, Jaegul ; Engelke, Ulrich ; Jena, Amit ; Dwyer, Tim. / Guidance in the human–machine analytics process. In: Visual Informatics. 2018 ; Vol. 2, No. 3. pp. 166-180.
@article{fc2e73ec3da74196a4f6cbc6da2761f0,
title = "Guidance in the human–machine analytics process",
abstract = "In this paper, we list the goals for and the pros and cons of guidance, and we discuss the role that it can play not only in key low-level visualization tasks but also the more sophisticated model-generation tasks of visual analytics. Recent advances in artificial intelligence, particularly in machine learning, have led to high hopes regarding the possibilities of using automatic techniques to perform some of the tasks that are currently done manually using visualization by data analysts. However, visual analytics remains a complex activity, combining many different subtasks. Some of these tasks are relatively low-level, and it is clear how automation could play a role—for example, classification and clustering of data. Other tasks are much more abstract and require significant human creativity, for example, linking insights gleaned from a variety of disparate and heterogeneous data artifacts to build support for decision making. In this paper, we outline the potential applications of guidance, as well as the inputs to guidance. We discuss challenges in implementing guidance, including the inputs to guidance systems and how to provide guidance to users. We propose potential methods for evaluating the quality of guidance at different phases in the analytic process and introduce the potential negative effects of guidance as a source of bias in analytic decision making.",
keywords = "Guidance, Model evaluation, Visual analytics",
author = "Christopher Collins and Natalia Andrienko and Tobias Schreck and Jing Yang and Jaegul Choo and Ulrich Engelke and Amit Jena and Tim Dwyer",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.visinf.2018.09.003",
language = "English",
volume = "2",
pages = "166--180",
journal = "Visual Informatics",
issn = "2543-2656",
publisher = "Elsevier BV",
number = "3",

}

TY - JOUR

T1 - Guidance in the human–machine analytics process

AU - Collins, Christopher

AU - Andrienko, Natalia

AU - Schreck, Tobias

AU - Yang, Jing

AU - Choo, Jaegul

AU - Engelke, Ulrich

AU - Jena, Amit

AU - Dwyer, Tim

PY - 2018/9/1

Y1 - 2018/9/1

N2 - In this paper, we list the goals for and the pros and cons of guidance, and we discuss the role that it can play not only in key low-level visualization tasks but also the more sophisticated model-generation tasks of visual analytics. Recent advances in artificial intelligence, particularly in machine learning, have led to high hopes regarding the possibilities of using automatic techniques to perform some of the tasks that are currently done manually using visualization by data analysts. However, visual analytics remains a complex activity, combining many different subtasks. Some of these tasks are relatively low-level, and it is clear how automation could play a role—for example, classification and clustering of data. Other tasks are much more abstract and require significant human creativity, for example, linking insights gleaned from a variety of disparate and heterogeneous data artifacts to build support for decision making. In this paper, we outline the potential applications of guidance, as well as the inputs to guidance. We discuss challenges in implementing guidance, including the inputs to guidance systems and how to provide guidance to users. We propose potential methods for evaluating the quality of guidance at different phases in the analytic process and introduce the potential negative effects of guidance as a source of bias in analytic decision making.

AB - In this paper, we list the goals for and the pros and cons of guidance, and we discuss the role that it can play not only in key low-level visualization tasks but also the more sophisticated model-generation tasks of visual analytics. Recent advances in artificial intelligence, particularly in machine learning, have led to high hopes regarding the possibilities of using automatic techniques to perform some of the tasks that are currently done manually using visualization by data analysts. However, visual analytics remains a complex activity, combining many different subtasks. Some of these tasks are relatively low-level, and it is clear how automation could play a role—for example, classification and clustering of data. Other tasks are much more abstract and require significant human creativity, for example, linking insights gleaned from a variety of disparate and heterogeneous data artifacts to build support for decision making. In this paper, we outline the potential applications of guidance, as well as the inputs to guidance. We discuss challenges in implementing guidance, including the inputs to guidance systems and how to provide guidance to users. We propose potential methods for evaluating the quality of guidance at different phases in the analytic process and introduce the potential negative effects of guidance as a source of bias in analytic decision making.

KW - Guidance

KW - Model evaluation

KW - Visual analytics

UR - http://www.scopus.com/inward/record.url?scp=85066730342&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066730342&partnerID=8YFLogxK

U2 - 10.1016/j.visinf.2018.09.003

DO - 10.1016/j.visinf.2018.09.003

M3 - Article

VL - 2

SP - 166

EP - 180

JO - Visual Informatics

JF - Visual Informatics

SN - 2543-2656

IS - 3

ER -