The Rational Agent Benchmark for Data Visualization

Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpre...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on visualization and computer graphics Vol. 30; no. 1; pp. 338 - 347
Main Authors Wu, Yifan, Guo, Ziyang, Mamakos, Michalis, Hartline, Jason, Hullman, Jessica
Format Journal Article
LanguageEnglish
Published United States IEEE 01.01.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects
Online AccessGet full text
ISSN1077-2626
1941-0506
1941-0506
DOI10.1109/TVCG.2023.3326513

Cover

Loading…
Abstract Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpreting visualization experiments. Our framework conceives two experiments with the same setup: one with behavioral agents (human subjects), and the other one with a hypothetical rational agent. A visualization is evaluated by comparing the expected performance of behavioral agents to that of a rational agent under different assumptions. Using recent visualization decision studies from the literature, we demonstrate how the framework can be used to pre-experimentally evaluate the experiment design by bounding the expected improvement in performance from having access to visualizations, and post-experimentally to deconfound errors of information extraction from errors of optimization, among other analyses.
AbstractList Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpreting visualization experiments. Our framework conceives two experiments with the same setup: one with behavioral agents (human subjects), and the other one with a hypothetical rational agent. A visualization is evaluated by comparing the expected performance of behavioral agents to that of a rational agent under different assumptions. Using recent visualization decision studies from the literature, we demonstrate how the framework can be used to pre-experimentally evaluate the experiment design by bounding the expected improvement in performance from having access to visualizations, and post-experimentally to deconfound errors of information extraction from errors of optimization, among other analyses.
Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpreting visualization experiments. Our framework conceives two experiments with the same setup: one with behavioral agents (human subjects), and the other one with a hypothetical rational agent. A visualization is evaluated by comparing the expected performance of behavioral agents to that of a rational agent under different assumptions. Using recent visualization decision studies from the literature, we demonstrate how the framework can be used to pre-experimentally evaluate the experiment design by bounding the expected improvement in performance from having access to visualizations, and post-experimentally to deconfound errors of information extraction from errors of optimization, among other analyses.Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study design, such as how useful the information that is visualized is for the task. We develop a rational agent framework for designing and interpreting visualization experiments. Our framework conceives two experiments with the same setup: one with behavioral agents (human subjects), and the other one with a hypothetical rational agent. A visualization is evaluated by comparing the expected performance of behavioral agents to that of a rational agent under different assumptions. Using recent visualization decision studies from the literature, we demonstrate how the framework can be used to pre-experimentally evaluate the experiment design by bounding the expected improvement in performance from having access to visualizations, and post-experimentally to deconfound errors of information extraction from errors of optimization, among other analyses.
Author Hullman, Jessica
Guo, Ziyang
Hartline, Jason
Wu, Yifan
Mamakos, Michalis
Author_xml – sequence: 1
  givenname: Yifan
  orcidid: 0000-0002-4299-8169
  surname: Wu
  fullname: Wu, Yifan
  email: yifan.wu@u.northwestern.edu
  organization: Northwestern University, USA
– sequence: 2
  givenname: Ziyang
  orcidid: 0009-0004-4200-6774
  surname: Guo
  fullname: Guo, Ziyang
  email: ziyangguo2027@u.northwestern.edu
  organization: Northwestern University, USA
– sequence: 3
  givenname: Michalis
  surname: Mamakos
  fullname: Mamakos, Michalis
  email: michailmamakos2022@u.northwestern.edu
  organization: Northwestern University, USA
– sequence: 4
  givenname: Jason
  orcidid: 0000-0001-5505-6819
  surname: Hartline
  fullname: Hartline, Jason
  email: hartline@northwestern.edu
  organization: Northwestern University, USA
– sequence: 5
  givenname: Jessica
  orcidid: 0000-0001-6826-3550
  surname: Hullman
  fullname: Hullman, Jessica
  email: jhullman@northwestern.edu
  organization: Northwestern University, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/37871058$$D View this record in MEDLINE/PubMed
BookMark eNp9kMtOwzAQRS1URB_wAUgIRWLDJsWPJLaXpUBBqoSESreW406oS5qUOFnA1-O0BaEuWHkW5874nj7qFGUBCJ0TPCQEy5vZfDwZUkzZkDGaxIQdoR6REQlxjJOOnzHnIU1o0kV951YYkygS8gR1GRec4Fj0EJstIXjRtS0LnQejNyjq4BYKs1zr6j3Iyiq407UO5tY1OrdfW_AUHWc6d3C2fwfo9eF-Nn4Mp8-Tp_FoGhoW4zoUlNKUp0JjkXKcJcBMqgkhCQdg1PAsozg1whhpGGSRYQudEk0lASpE5FsN0PVu76YqPxpwtVpbZyDPdQFl45THCI24jCOPXh2gq7KpfCVPSZzEgrOkXXi5p5p0DQu1qayv-al-dHiA7ABTlc5VkP0iBKtWuWqVq1a52iv3GX6QMbbeeqorbfN_kxe7pAWAP5f8j6WM2DfNT4ug
CODEN ITVGEA
CitedBy_id crossref_primary_10_1109_MCG_2024_3360881
crossref_primary_10_1109_TVCG_2024_3456182
Cites_doi 10.1073/pnas.1915841117
10.1038/s41586-021-03659-0
10.1109/tvcg.2021.3114813
10.1145/3490486.3538338
10.1017/s0140525x20001685
10.1038/nrn3475
10.1109/tvcg.2019.2934287
10.1179/1743277414y.0000000099
10.1109/tvcg.2013.126
10.1162/99608f92.3ab8a587
10.1109/tvcg.2011.279
10.1145/1168149.1168158
10.1117/12.643631
10.1145/1377966.1377974
10.1109/TVCG.2023.3326516
10.1080/01621459.1984.10478080
10.1109/tvcg.2020.3030335
10.1145/3173574.3173718
10.1017/CBO9780511984037
10.1037/a0024558
10.1109/tvcg.2021.3114824
10.1371/journal.pone.0142444
10.1109/tvcg.2009.111
10.1109/tvcg.2018.2864889
10.1142/9789814417358_0006
10.1109/tvcg.2020.3028984
10.1145/2858036.2858558
10.1145/1600150.1600175
10.1109/tvcg.2020.3030395
10.1086/718371
10.1002/acp.2932
10.1109/visual.2005.1532781
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TVCG.2023.3326513
DatabaseName IEEE Xplore (IEEE)
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Technology Research Database
Computer and Information Systems Abstracts – Academic
Electronics & Communications Abstracts
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitleList Technology Research Database
PubMed

MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1941-0506
EndPage 347
ExternalDocumentID 37871058
10_1109_TVCG_2023_3326513
10290994
Genre orig-research
Journal Article
GroupedDBID ---
-~X
.DC
0R~
29I
4.4
53G
5GY
5VS
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IEDLZ
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
PQQKQ
RIA
RIE
RNI
RNS
RZB
TN5
VH1
AAYOK
AAYXX
CITATION
RIG
NPM
7SC
7SP
8FD
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c350t-8222b7b8a08b70f6e3cba11167ee32c7ff20bc8cc9c3ef4c3dab1a291e2884023
IEDL.DBID RIE
ISSN 1077-2626
1941-0506
IngestDate Fri Jul 11 00:30:13 EDT 2025
Mon Jun 30 06:35:10 EDT 2025
Mon Jul 21 06:06:34 EDT 2025
Tue Jul 01 02:12:19 EDT 2025
Thu Apr 24 23:02:08 EDT 2025
Wed Aug 27 02:12:08 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
License https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
https://doi.org/10.15223/policy-029
https://doi.org/10.15223/policy-037
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c350t-8222b7b8a08b70f6e3cba11167ee32c7ff20bc8cc9c3ef4c3dab1a291e2884023
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0001-6826-3550
0009-0004-4200-6774
0000-0002-4299-8169
0000-0001-5505-6819
PMID 37871058
PQID 2906587362
PQPubID 75741
PageCount 10
ParticipantIDs pubmed_primary_37871058
proquest_journals_2906587362
crossref_primary_10_1109_TVCG_2023_3326513
ieee_primary_10290994
crossref_citationtrail_10_1109_TVCG_2023_3326513
proquest_miscellaneous_2881247954
ProviderPackageCode CITATION
AAYXX
PublicationCentury 2000
PublicationDate 2024-01-01
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – month: 01
  year: 2024
  text: 2024-01-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: New York
PublicationTitle IEEE transactions on visualization and computer graphics
PublicationTitleAbbrev TVCG
PublicationTitleAlternate IEEE Trans Vis Comput Graph
PublicationYear 2024
Publisher IEEE
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml – name: IEEE
– name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References ref13
ref12
ref15
ref14
ref31
ref30
ref11
ref33
ref10
ref32
ref2
ref1
ref17
ref16
ref19
ref18
Coe (ref4) 2002; 12
Knill (ref24) 1996
ref23
ref26
ref25
ref20
ref22
ref21
ref28
ref27
ref29
ref8
ref7
ref9
ref3
ref6
ref5
References_xml – volume: 12
  start-page: 14
  volume-title: British Educational Research Association Annual Conference
  year: 2002
  ident: ref4
  article-title: Its the effect size, stupid
– ident: ref1
  doi: 10.1073/pnas.1915841117
– ident: ref10
  doi: 10.1038/s41586-021-03659-0
– ident: ref5
  doi: 10.1109/tvcg.2021.3114813
– ident: ref26
  doi: 10.1145/3490486.3538338
– ident: ref32
  doi: 10.1017/s0140525x20001685
– ident: ref2
  doi: 10.1038/nrn3475
– ident: ref11
  doi: 10.1109/tvcg.2019.2934287
– ident: ref23
  doi: 10.1179/1743277414y.0000000099
– ident: ref16
  doi: 10.1109/tvcg.2013.126
– ident: ref12
  doi: 10.1162/99608f92.3ab8a587
– ident: ref25
  doi: 10.1109/tvcg.2011.279
– ident: ref30
  doi: 10.1145/1168149.1168158
– ident: ref33
  doi: 10.1117/12.643631
– ident: ref15
  doi: 10.1145/1377966.1377974
– ident: ref18
  doi: 10.1109/TVCG.2023.3326516
– ident: ref3
  doi: 10.1080/01621459.1984.10478080
– ident: ref19
  doi: 10.1109/tvcg.2020.3030335
– ident: ref6
  doi: 10.1145/3173574.3173718
– start-page: 825
  volume-title: Perception as Bayesian Inference
  year: 1996
  ident: ref24
  doi: 10.1017/CBO9780511984037
– ident: ref8
  doi: 10.1037/a0024558
– ident: ref20
  doi: 10.1109/tvcg.2021.3114824
– ident: ref14
  doi: 10.1371/journal.pone.0142444
– ident: ref28
  doi: 10.1109/tvcg.2009.111
– ident: ref13
  doi: 10.1109/tvcg.2018.2864889
– ident: ref17
  doi: 10.1142/9789814417358_0006
– ident: ref22
  doi: 10.1109/tvcg.2020.3028984
– ident: ref21
  doi: 10.1145/2858036.2858558
– ident: ref27
  doi: 10.1145/1600150.1600175
– ident: ref9
  doi: 10.1109/tvcg.2020.3030395
– ident: ref7
  doi: 10.1086/718371
– ident: ref29
  doi: 10.1002/acp.2932
– ident: ref31
  doi: 10.1109/visual.2005.1532781
SSID ssj0014489
Score 2.4297926
Snippet Understanding how helpful a visualization is from experimental results is difficult because the observed performance is confounded with aspects of the study...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 338
SubjectTerms Bayes methods
Behavioral sciences
Benchmark testing
Data visualization
decision-making
Design of experiments
Errors
Evaluation
Information retrieval
rational agent
Scientific visualization
scoring rule
Task analysis
Uncertainty
Visualization
Title The Rational Agent Benchmark for Data Visualization
URI https://ieeexplore.ieee.org/document/10290994
https://www.ncbi.nlm.nih.gov/pubmed/37871058
https://www.proquest.com/docview/2906587362
https://www.proquest.com/docview/2881247954
Volume 30
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT8MwDLaAExx4DhgMVCROSC1p0kdyHI8xIcEBMcStStJMIGBD0F349dhNNwESiFulpkmaz5G_2LENcIiQk55gYZmVLET-70JjpQ2lynQuszzJSrJDXl1n_UFyeZ_eN8HqdSyMc66-fOYieqx9-eXYTshUhjucK2Q0yTzM48nNB2vNXAY4jvIXDPOQI01vXJgxU8e3d6cXEdUJjwSylTSm4jkCJRW5hfymj-oCK79zzVrn9Fbgejpbf9XkKZpUJrIfPxI5_vt3VmG5YZ9B14vLGsy50TosfclJuAECBSe4aUyEQZcir4ITFOWHF_32FCDFDc50pYO7x3cKx_RBnC0Y9M5vT_thU1khtCJlVUiswORGaiZNzoaZE9bomFwyzglu8-GQM4LMKivcMLGi1CbWXMWOSzwRcrEJC6PxyG1DkJaxsJlT2IFMnIoNJcTjWqbcskxZ3gY2Xd_CNmnHqfrFc1EfP5gqCJ2C0CkadNpwNPvk1efc-Ktxi1b2S0O_qG3oTFEsmm35XlBu-1TmqLTbcDB7jRuKvCR65MYTbCOJ8-QqxS62PPqzzqdCs_PLoLuwiHNLvImmAwvV28TtIWmpzH4trJ_3BuJC
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT-MwEB7xOOxy4LHLozyzEqeVEhw7D_vIu7x6WBXELbIdV6BCiyC98OuZidMKkFhxixTHdvyNNZ9nPDMAuwg56QkWllnJQuT_LjRW2lCqTOcyy5OsJDvkVSdrXyfnt-ltE6xex8I45-rLZy6ix9qXXw7tiExluMO5QkaTTMMsKv409uFaE6cBjqT8FcM85EjUGydmzNRe9-bwNKJK4ZFAvpLGVD5HoKwiu5AfNFJdYuVrtllrnZMF6Izn6y-b9KNRZSL7-imV47d_aBHmG_4Z7HuBWYIpN_gFc--yEv4GgaIT_GuMhME-xV4FByjMd4_6uR8gyQ2OdKWDm_sXCsj0YZzLcH1y3D1sh01thdCKlFUh8QKTG6mZNDnrZU5Yo2NyyjgnuM17Pc4INKuscL3EilKbWHMVOy7xTMjFCswMhgO3BkFaxsJmTmEHMnEqNpQSj2uZcssyZXkL2Hh9C9skHqf6Fw9FfQBhqiB0CkKnaNBpwd_JJ08-68b_Gi_Tyr5r6Be1BZtjFItmY74UlN0-lTmq7Rb8mbzGLUV-Ej1wwxG2kcR6cpViF6se_UnnY6FZ_2LQHfjR7l5dFpdnnYsN-InzTLzBZhNmqueR20IKU5ntWnDfAPGj5Ys
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=The+Rational+Agent+Benchmark+for+Data+Visualization&rft.jtitle=IEEE+transactions+on+visualization+and+computer+graphics&rft.au=Wu%2C+Yifan&rft.au=Guo%2C+Ziyang&rft.au=Mamakos%2C+Michalis&rft.au=Hartline%2C+Jason&rft.date=2024-01-01&rft.issn=1941-0506&rft.eissn=1941-0506&rft.volume=30&rft.issue=1&rft.spage=338&rft_id=info:doi/10.1109%2FTVCG.2023.3326513&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1077-2626&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1077-2626&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1077-2626&client=summon