Predicting intent behind selections in scatterplot visualizations

Gadhave, Kiran; Görtler, Jochen; Cutler, Zach; Nobre, Carolina; Deussen, Oliver; Meyer, Miriah; Phillips, Jeff M.; Lex, Alexander

Predicting intent behind selections in scatterplot visualizations

Dateien

Gadhave_2-lu8hwkr6ntaj2.pdfGröße: 3.47 MBDownloads: 615

Datum

2021

Autor:innen

Gadhave, Kiran

Görtler, Jochen

Cutler, Zach

Nobre, Carolina

Deussen, Oliver

Meyer, Miriah

Phillips, Jeff M.

Lex, Alexander

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

Information Visualization. Sage Publications. 2021, 20(4), pp. 207-228. ISSN 1473-8716. eISSN 1473-8724. Available under: doi: 10.1177/14738716211038604

Zusammenfassung

Predicting and capturing an analyst’s intent behind a selection in a data visualization is valuable in two scenarios: First, a successful prediction of a pattern an analyst intended to select can be used to auto-complete a partial selection which, in turn, can improve the correctness of the selection. Second, knowing the intent behind a selection can be used to improve recall and reproducibility. In this paper, we introduce methods to infer analyst’s intents behind selections in data visualizations, such as scatterplots. We describe intents based on patterns in the data, and identify algorithms that can capture these patterns. Upon an interactive selection, we compare the selected items with the results of a large set of computed patterns, and use various ranking approaches to identify the best pattern for an analyst’s selection. We store annotations and the metadata to reconstruct a selection, such as the type of algorithm and its parameterization, in a provenance graph. We present a prototype system that implements these methods for tabular data and scatterplots. Analysts can select a prediction to auto-complete partial selections and to seamlessly log their intents. We discuss implications of our approach for reproducibility and reuse of analysis workflows. We evaluate our approach in a crowd-sourced study, where we show that auto-completing selection improves accuracy, and that we can accurately capture pattern-based intent.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Provenance, reproducibility, intent, brushing, selections

Zitieren

ISO 690

GADHAVE, Kiran, Jochen GÖRTLER, Zach CUTLER, Carolina NOBRE, Oliver DEUSSEN, Miriah MEYER, Jeff M. PHILLIPS, Alexander LEX, 2021. Predicting intent behind selections in scatterplot visualizations. In: Information Visualization. Sage Publications. 2021, 20(4), pp. 207-228. ISSN 1473-8716. eISSN 1473-8724. Available under: doi: 10.1177/14738716211038604

BibTex

@article{Gadhave2021Predi-54767,
  year={2021},
  doi={10.1177/14738716211038604},
  title={Predicting intent behind selections in scatterplot visualizations},
  number={4},
  volume={20},
  issn={1473-8716},
  journal={Information Visualization},
  pages={207--228},
  author={Gadhave, Kiran and Görtler, Jochen and Cutler, Zach and Nobre, Carolina and Deussen, Oliver and Meyer, Miriah and Phillips, Jeff M. and Lex, Alexander}
}

RDF

<rdf:RDF
    xmlns:dcterms="http://purl.org/dc/terms/"
    xmlns:dc="http://purl.org/dc/elements/1.1/"
    xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
    xmlns:bibo="http://purl.org/ontology/bibo/"
    xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#"
    xmlns:foaf="http://xmlns.com/foaf/0.1/"
    xmlns:void="http://rdfs.org/ns/void#"
    xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > 
  <rdf:Description rdf:about="https://kops.uni-konstanz.de/server/rdf/resource/123456789/54767">
    <dc:contributor>Nobre, Carolina</dc:contributor>
    <dc:creator>Phillips, Jeff M.</dc:creator>
    <dcterms:issued>2021</dcterms:issued>
    <dc:contributor>Deussen, Oliver</dc:contributor>
    <dc:contributor>Meyer, Miriah</dc:contributor>
    <dc:creator>Cutler, Zach</dc:creator>
    <dc:creator>Deussen, Oliver</dc:creator>
    <dc:language>eng</dc:language>
    <dc:contributor>Phillips, Jeff M.</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/54767"/>
    <dc:creator>Nobre, Carolina</dc:creator>
    <dc:creator>Görtler, Jochen</dc:creator>
    <dc:contributor>Gadhave, Kiran</dc:contributor>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-09-01T13:46:43Z</dcterms:available>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Cutler, Zach</dc:contributor>
    <dcterms:title>Predicting intent behind selections in scatterplot visualizations</dcterms:title>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:abstract xml:lang="eng">Predicting and capturing an analyst’s intent behind a selection in a data visualization is valuable in two scenarios: First, a successful prediction of a pattern an analyst intended to select can be used to auto-complete a partial selection which, in turn, can improve the correctness of the selection. Second, knowing the intent behind a selection can be used to improve recall and reproducibility. In this paper, we introduce methods to infer analyst’s intents behind selections in data visualizations, such as scatterplots. We describe intents based on patterns in the data, and identify algorithms that can capture these patterns. Upon an interactive selection, we compare the selected items with the results of a large set of computed patterns, and use various ranking approaches to identify the best pattern for an analyst’s selection. We store annotations and the metadata to reconstruct a selection, such as the type of algorithm and its parameterization, in a provenance graph. We present a prototype system that implements these methods for tabular data and scatterplots. Analysts can select a prediction to auto-complete partial selections and to seamlessly log their intents. We discuss implications of our approach for reproducibility and reuse of analysis workflows. We evaluate our approach in a crowd-sourced study, where we show that auto-completing selection improves accuracy, and that we can accurately capture pattern-based intent.</dcterms:abstract>
    <dc:rights>terms-of-use</dc:rights>
    <dc:creator>Gadhave, Kiran</dc:creator>
    <dc:creator>Meyer, Miriah</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-09-01T13:46:43Z</dc:date>
    <dc:contributor>Lex, Alexander</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54767/1/Gadhave_2-lu8hwkr6ntaj2.pdf"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54767/1/Gadhave_2-lu8hwkr6ntaj2.pdf"/>
    <dc:contributor>Görtler, Jochen</dc:contributor>
    <dc:creator>Lex, Alexander</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja