Progressive Learning of Topic Modeling Parameters : A Visual Analytics Framework


Dateien zu dieser Ressource

Dateien Größe Format Anzeige

Zu diesem Dokument gibt es keine Dateien.

EL-ASSADY, Mennatallah, Rita SEVASTJANOVA, Fabian SPERRLE, Daniel KEIM, Christopher COLLINS, 2018. Progressive Learning of Topic Modeling Parameters : A Visual Analytics Framework. In: IEEE Transactions on Visualization and Computer Graphics. 24(1), pp. 382-391. ISSN 1077-2626. eISSN 1941-0506. Available under: doi: 10.1109/TVCG.2017.2745080

@article{ElAssady2018-01Progr-41238, title={Progressive Learning of Topic Modeling Parameters : A Visual Analytics Framework}, year={2018}, doi={10.1109/TVCG.2017.2745080}, number={1}, volume={24}, issn={1077-2626}, journal={IEEE Transactions on Visualization and Computer Graphics}, pages={382--391}, author={El-Assady, Mennatallah and Sevastjanova, Rita and Sperrle, Fabian and Keim, Daniel and Collins, Christopher} }

<rdf:RDF xmlns:dcterms="" xmlns:dc="" xmlns:rdf="" xmlns:bibo="" xmlns:dspace="" xmlns:foaf="" xmlns:void="" xmlns:xsd="" > <rdf:Description rdf:about=""> <dcterms:title>Progressive Learning of Topic Modeling Parameters : A Visual Analytics Framework</dcterms:title> <dc:creator>Collins, Christopher</dc:creator> <dspace:isPartOfCollection rdf:resource=""/> <dc:date rdf:datatype="">2018-02-06T10:19:48Z</dc:date> <dc:contributor>Sperrle, Fabian</dc:contributor> <dc:contributor>Sevastjanova, Rita</dc:contributor> <dc:contributor>Keim, Daniel</dc:contributor> <bibo:uri rdf:resource=""/> <dc:contributor>Collins, Christopher</dc:contributor> <dcterms:abstract xml:lang="eng">Topic modeling algorithms are widely used to analyze the thematic composition of text corpora but remain difficult to interpret and adjust. Addressing these limitations, we present a modular visual analytics framework, tackling the understandability and adaptability of topic models through a user-driven reinforcement learning process which does not require a deep understanding of the underlying topic modeling algorithms. Given a document corpus, our approach initializes two algorithm configurations based on a parameter space analysis that enhances document separability. We abstract the model complexity in an interactive visual workspace for exploring the automatic matching results of two models, investigating topic summaries, analyzing parameter distributions, and reviewing documents. The main contribution of our work is an iterative decision-making technique in which users provide a document-based relevance feedback that allows the framework to converge to a user-endorsed topic distribution. We also report feedback from a two-stage study which shows that our technique results in topic model quality improvements on two independent measures.</dcterms:abstract> <dc:creator>Sperrle, Fabian</dc:creator> <dc:contributor>El-Assady, Mennatallah</dc:contributor> <dcterms:issued>2018-01</dcterms:issued> <dc:language>eng</dc:language> <dc:creator>Sevastjanova, Rita</dc:creator> <dcterms:isPartOf rdf:resource=""/> <dc:creator>Keim, Daniel</dc:creator> <dc:creator>El-Assady, Mennatallah</dc:creator> <dcterms:available rdf:datatype="">2018-02-06T10:19:48Z</dcterms:available> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> </rdf:Description> </rdf:RDF>

Das Dokument erscheint in:

KOPS Suche


Mein Benutzerkonto