QuestionComb : A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling

Sevastjanova, Rita; Jentner, Wolfgang; Sperrle, Fabian; Kehlbeck, Rebecca; Bernard, Jürgen; El-Assady, Mennatallah

QuestionComb : A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling

Dateien

Sevastjanova_2-na7l1ozzvmqe8.pdfGröße: 2.88 MBDownloads: 211

Datum

2021

Autor:innen

Bernard, Jürgen

El-Assady, Mennatallah

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Zeitschriftenartikel

Publikationsstatus

Published

Erschienen in

ACM Transactions on Interactive Intelligent Systems. ACM. 2021, 11(3-4), 19. ISSN 2160-6455. Available under: doi: 10.1145/3429448

Zusammenfassung

Linguistic insight in the form of high-level relationships and rules in text builds the basis of our understanding of language. However, the data-driven generation of such structures often lacks labeled resources that can be used as training data for supervised machine learning. The creation of such ground-truth data is a time-consuming process that often requires domain expertise to resolve text ambiguities and characterize linguistic phenomena. Furthermore, the creation and refinement of machine learning models is often challenging for linguists as the models are often complex, in-transparent, and difficult to understand. To tackle these challenges, we present a visual analytics technique for interactive data labeling that applies concepts from gamification and explainable Artificial Intelligence (XAI) to support complex classification tasks. The visual-interactive labeling interface promotes the creation of effective training data. Visual explanations of learned rules unveil the decisions of the machine learning model and support iterative and interactive optimization. The gamification-inspired design guides the user through the labeling process and provides feedback on the model performance. As an instance of the proposed technique, we present QuestionComb, a workspace tailored to the task of question classification (i.e., in information-seeking vs. non-information-seeking questions). Our evaluation studies confirm that gamification concepts are beneficial to engage users through continuous feedback, offering an effective visual analytics technique when combined with active learning and XAI.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

Visual interactive labeling, active learning, explainable artificial intelligence, gamification

Zitieren

ISO 690

SEVASTJANOVA, Rita, Wolfgang JENTNER, Fabian SPERRLE, Rebecca KEHLBECK, Jürgen BERNARD, Mennatallah EL-ASSADY, 2021. QuestionComb : A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling. In: ACM Transactions on Interactive Intelligent Systems. ACM. 2021, 11(3-4), 19. ISSN 2160-6455. Available under: doi: 10.1145/3429448

BibTex

@article{Sevastjanova2021Quest-54903,
  year={2021},
  doi={10.1145/3429448},
  title={QuestionComb : A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling},
  number={3-4},
  volume={11},
  issn={2160-6455},
  journal={ACM Transactions on Interactive Intelligent Systems},
  author={Sevastjanova, Rita and Jentner, Wolfgang and Sperrle, Fabian and Kehlbeck, Rebecca and Bernard, Jürgen and El-Assady, Mennatallah},
  note={Article Number: 19}
}

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/123456789/54903">
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/54903"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:contributor>Sevastjanova, Rita</dc:contributor>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-09-20T14:14:19Z</dc:date>
    <dc:contributor>Kehlbeck, Rebecca</dc:contributor>
    <dcterms:issued>2021</dcterms:issued>
    <dc:creator>Kehlbeck, Rebecca</dc:creator>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54903/3/Sevastjanova_2-na7l1ozzvmqe8.pdf"/>
    <dcterms:title>QuestionComb : A Gamification Approach for the Visual Explanation of Linguistic Phenomena through Interactive Labeling</dcterms:title>
    <dc:language>eng</dc:language>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54903/3/Sevastjanova_2-na7l1ozzvmqe8.pdf"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dc:creator>Sevastjanova, Rita</dc:creator>
    <dc:contributor>Bernard, Jürgen</dc:contributor>
    <dc:creator>Sperrle, Fabian</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Jentner, Wolfgang</dc:contributor>
    <dc:contributor>Sperrle, Fabian</dc:contributor>
    <dcterms:abstract xml:lang="eng">Linguistic insight in the form of high-level relationships and rules in text builds the basis of our understanding of language. However, the data-driven generation of such structures often lacks labeled resources that can be used as training data for supervised machine learning. The creation of such ground-truth data is a time-consuming process that often requires domain expertise to resolve text ambiguities and characterize linguistic phenomena. Furthermore, the creation and refinement of machine learning models is often challenging for linguists as the models are often complex, in-transparent, and difficult to understand. To tackle these challenges, we present a visual analytics technique for interactive data labeling that applies concepts from gamification and explainable Artificial Intelligence (XAI) to support complex classification tasks. The visual-interactive labeling interface promotes the creation of effective training data. Visual explanations of learned rules unveil the decisions of the machine learning model and support iterative and interactive optimization. The gamification-inspired design guides the user through the labeling process and provides feedback on the model performance. As an instance of the proposed technique, we present QuestionComb, a workspace tailored to the task of question classification (i.e., in information-seeking vs. non-information-seeking questions). Our evaluation studies confirm that gamification concepts are beneficial to engage users through continuous feedback, offering an effective visual analytics technique when combined with active learning and XAI.</dcterms:abstract>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-09-20T14:14:19Z</dcterms:available>
    <dc:creator>Bernard, Jürgen</dc:creator>
    <dc:creator>Jentner, Wolfgang</dc:creator>
  </rdf:Description>
</rdf:RDF>

Universitätsbibliographie

Ja

Begutachtet

Ja