Visual Analytics for the Prediction of Movie Rating and Box Ofﬁce Performance

This paper describes our solution to the IEEE VAST 2013 Mini Challenge 11. The task of the challenge was to create a visual and interactive tool to predict the popularity of new movies in terms of viewer ratings and ticket sales for the opening weekend in the U.S. The data usage was restricted by the challenge organizers to data from the Internet Movie Database (IMDb)2 and a predefined set of Twitter3 microblog messages. To tackle the challenge we designed a system together with an analysis workflow, combining machine learning and visualization paradigms in order to obtain accurate predictions. In Section 2 we describe the machine learning components used within the analysis workflow. Next, in Section 3, we describe where and how the human analyst is enabled to enhance the prediction with her/his world knowledge. Finally, Section 4 concludes the paper providing an evaluation of the prediction accuracy with and without human intervention.

Subject (DDC)

004 Computer Science

Conference

VIS, Oct 13, 2013 - Oct 18, 2013, Atlanta, Georgia, USA

Cite This

ISO 690

EL-ASSADY, Mennatallah, Daniel HAFNER, Michael BLUMENSCHEIN, Alexander JӒGER, Wolfgang JENTNER, Christian ROHRDANTZ, Fabian FISCHER, Svenja SIMON, Tobias SCHRECK, Daniel A. KEIM, 2013. Visual Analytics for the Prediction of Movie Rating and Box Ofﬁce Performance. VIS. Atlanta, Georgia, USA, Oct 13, 2013 - Oct 18, 2013. In: VIS 2013 : IEEE International Conference on Visual Analytics Science and Technology ; 13 - 18 October 2013, Atlanta, Georgia, USA

BibTex

@inproceedings{ElAssady2013Visua-26533,
  year={2013},
  title={Visual Analytics for the Prediction of Movie Rating and Box Ofﬁce Performance},
  booktitle={VIS 2013 : IEEE International Conference on Visual Analytics Science and Technology ; 13 - 18 October 2013, Atlanta, Georgia, USA},
  author={El-Assady, Mennatallah and Hafner, Daniel and Blumenschein, Michael and Jӓger, Alexander and Jentner, Wolfgang and Rohrdantz, Christian and Fischer, Fabian and Simon, Svenja and Schreck, Tobias and Keim, Daniel A.}
}

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/123456789/26533">
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:contributor>Rohrdantz, Christian</dc:contributor>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/26533/2/Hafner_265333.pdf"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dcterms:title>Visual Analytics for the Prediction of Movie Rating and Box Ofﬁce Performance</dcterms:title>
    <dc:creator>El-Assady, Mennatallah</dc:creator>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:language>eng</dc:language>
    <dc:rights>terms-of-use</dc:rights>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Blumenschein, Michael</dc:creator>
    <dc:creator>Jentner, Wolfgang</dc:creator>
    <dc:creator>Rohrdantz, Christian</dc:creator>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:creator>Schreck, Tobias</dc:creator>
    <bibo:uri rdf:resource="http://kops.uni-konstanz.de/handle/123456789/26533"/>
    <dc:creator>Hafner, Daniel</dc:creator>
    <dc:creator>Simon, Svenja</dc:creator>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-02-26T10:50:39Z</dc:date>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/26533/2/Hafner_265333.pdf"/>
    <dcterms:issued>2013</dcterms:issued>
    <dc:contributor>Hafner, Daniel</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dc:contributor>Simon, Svenja</dc:contributor>
    <dc:contributor>Blumenschein, Michael</dc:contributor>
    <dc:creator>Jӓger, Alexander</dc:creator>
    <dcterms:bibliographicCitation>VIS 2013 : IEEE International Conference on Visual Analytics Science and Technology ; 13-18 October 2013, Atlanta, Georgia, USA</dcterms:bibliographicCitation>
    <dc:contributor>Jentner, Wolfgang</dc:contributor>
    <dc:contributor>Fischer, Fabian</dc:contributor>
    <dc:contributor>Jӓger, Alexander</dc:contributor>
    <dc:creator>Fischer, Fabian</dc:creator>
    <dc:contributor>Schreck, Tobias</dc:contributor>
    <dcterms:abstract xml:lang="eng">This paper describes our solution to the IEEE VAST 2013 Mini Challenge 11. The task of the challenge was to create a visual and interactive tool to predict the popularity of new movies in terms of viewer ratings and ticket sales for the opening weekend in the U.S. The data usage was restricted by the challenge organizers to data from the Internet Movie Database (IMDb)2 and a predefined set of Twitter3 microblog messages. To tackle the challenge we designed a system together with an analysis workflow, combining machine learning and visualization paradigms in order to obtain accurate predictions. In Section 2 we describe the machine learning components used within the analysis workflow. Next, in Section 3, we describe where and how the human analyst is enabled to enhance the prediction with her/his world knowledge. Finally, Section 4 concludes the paper providing an evaluation of the prediction accuracy with and without human intervention.</dcterms:abstract>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2014-02-26T10:50:39Z</dcterms:available>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
    <dc:contributor>El-Assady, Mennatallah</dc:contributor>
  </rdf:Description>
</rdf:RDF>

Bibliography of Konstanz

Yes