Publikation: Learning Contextualized User Preferences for Co‐Adaptive Guidance in Mixed‐Initiative Topic Model Refinement
Dateien
Datum
Herausgeber:innen
ISSN der Zeitschrift
Electronic ISSN
ISBN
Bibliografische Daten
Verlag
Schriftenreihe
Auflagebezeichnung
URI (zitierfähiger Link)
DOI (zitierfähiger Link)
Internationale Patentnummer
Link zur Lizenz
Angaben zur Forschungsförderung
Projekt
Open Access-Veröffentlichung
Core Facility der Universität Konstanz
Titel in einer weiteren Sprache
Publikationstyp
Publikationsstatus
Erschienen in
Zusammenfassung
Mixed-initiative visual analytics systems support collaborative human-machine decision-making processes. However, many multi-objective optimization tasks, such as topic model refinement, are highly subjective and context-dependent. Hence, systems need to adapt their optimization suggestions throughout the interactive refinement process to provide efficient guidance. To tackle this challenge, we present a technique for learning context-dependent user preferences and demonstrate its applicability to topic model refinement. We deploy agents with distinct associated optimization strategies that compete for the user's acceptance of their suggestions. To decide when to provide guidance, each agent maintains an intelligible, rule-based classifier over context vectorizations that captures the development of quality metrics between distinct analysis states. By observing implicit and explicit user feedback, agents learn in which contexts to provide their specific guidance operation. An agent in topic model refinement might, for example, learn to react to declining model coherence by suggesting to split a topic. Our results confirm that the rules learned by agents capture contextual user preferences. Further, we show that the learned rules are transferable between similar datasets, avoiding common cold-start problems and enabling a continuous refinement of agents across corpora.
Zusammenfassung in einer weiteren Sprache
Fachgebiet (DDC)
Schlagwörter
Konferenz
Rezension
Zitieren
ISO 690
SPERRLE, Fabian, Hanna SCHÄFER, Daniel A. KEIM, Mennatallah EL-ASSADY, 2021. Learning Contextualized User Preferences for Co‐Adaptive Guidance in Mixed‐Initiative Topic Model Refinement. In: Computer Graphics Forum. Wiley. 2021, 40(3), pp. 215-226. ISSN 0167-7055. eISSN 1467-8659. Available under: doi: 10.1111/cgf.14301BibTex
@article{Sperrle2021Learn-54161, year={2021}, doi={10.1111/cgf.14301}, title={Learning Contextualized User Preferences for Co‐Adaptive Guidance in Mixed‐Initiative Topic Model Refinement}, number={3}, volume={40}, issn={0167-7055}, journal={Computer Graphics Forum}, pages={215--226}, author={Sperrle, Fabian and Schäfer, Hanna and Keim, Daniel A. and El-Assady, Mennatallah} }
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/123456789/54161"> <dc:rights>Attribution-NonCommercial-NoDerivatives 4.0 International</dc:rights> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/54161"/> <dc:contributor>Schäfer, Hanna</dc:contributor> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-06-30T14:02:53Z</dcterms:available> <dcterms:rights rdf:resource="http://creativecommons.org/licenses/by-nc-nd/4.0/"/> <dc:contributor>Keim, Daniel A.</dc:contributor> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dc:creator>El-Assady, Mennatallah</dc:creator> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dcterms:title>Learning Contextualized User Preferences for Co‐Adaptive Guidance in Mixed‐Initiative Topic Model Refinement</dcterms:title> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2021-06-30T14:02:53Z</dc:date> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54161/1/Sperrle_2-1puacsni9ezc06.pdf"/> <dc:creator>Keim, Daniel A.</dc:creator> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/54161/1/Sperrle_2-1puacsni9ezc06.pdf"/> <dcterms:issued>2021</dcterms:issued> <dc:creator>Sperrle, Fabian</dc:creator> <dc:contributor>Sperrle, Fabian</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dc:language>eng</dc:language> <foaf:homepage rdf:resource="http://localhost:8080/"/> <dc:creator>Schäfer, Hanna</dc:creator> <dcterms:abstract xml:lang="eng">Mixed-initiative visual analytics systems support collaborative human-machine decision-making processes. However, many multi-objective optimization tasks, such as topic model refinement, are highly subjective and context-dependent. Hence, systems need to adapt their optimization suggestions throughout the interactive refinement process to provide efficient guidance. To tackle this challenge, we present a technique for learning context-dependent user preferences and demonstrate its applicability to topic model refinement. We deploy agents with distinct associated optimization strategies that compete for the user's acceptance of their suggestions. To decide when to provide guidance, each agent maintains an intelligible, rule-based classifier over context vectorizations that captures the development of quality metrics between distinct analysis states. By observing implicit and explicit user feedback, agents learn in which contexts to provide their specific guidance operation. An agent in topic model refinement might, for example, learn to react to declining model coherence by suggesting to split a topic. Our results confirm that the rules learned by agents capture contextual user preferences. Further, we show that the learned rules are transferable between similar datasets, avoiding common cold-start problems and enabling a continuous refinement of agents across corpora.</dcterms:abstract> </rdf:Description> </rdf:RDF>