Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web

Kwon, Bum Chul; Choo, Jaegul; Kim, Sung-Hee; Keim, Daniel A.; Park, Haesun; Yi, Ji Soo

Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web

Dateien

Kwon_0-301049.pdfGröße: 380.46 KBDownloads: 116

Datum

2015

Autor:innen

Kwon, Bum Chul

Choo, Jaegul

Kim, Sung-Hee

Keim, Daniel A.

Park, Haesun

Yi, Ji Soo

URI (zitierfähiger Link)

http://nbn-resolving.de/urn:nbn:de:bsz:352-0-301049

Link zur Lizenz

Urheberrechtlich geschützt

Open Access-Veröffentlichung

Open Access Green

Sammlungen

Informatik und Informationswissenschaft

Publikationstyp

Beitrag zu einem Konferenzband

Publikationsstatus

Published

Erschienen in

POLO CHAU, , ed. and others. Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics Permission. New York: ACM, 2015, pp. 47-55

Zusammenfassung

Despite recent improvements in computational approaches such as
machine learning, natural language processing, and computational
linguistics, making a computer understand human-generated unstructured
text still remains a difficult problem to solve. To alleviate
the challenges, we propose an approach called “Opinion Marks,”
which enables writers to mark positive and negative aspects of a
topic on their own text. In addition, Opinion Marks incorporates an
automatic marking suggestion algorithm to offload a user’s marking
effort. The phrases marked with Opinion Marks can be further
used to clarify the sentiments of other text in a similar context.
We implemented Opinion Marks at a question answering website
http://caniask.net. To test the efficacy of Opinion Marks, we
conducted a crowdsourced experiment with 144 participants in a
between-subject design under three different conditions: 1) human
marking only; 2) machine marking only (automatic marking suggestion);
and 3) human-machine collaboration (Opinion Marks).
This study revealed that Opinion Marks significantly improves the
quality of marked phrases and usability of the system.

Fachgebiet (DDC)

004 Informatik

Schlagwörter

human-based computation, user interface, crowdsourcing

Konferenz

KDD 2015 Workshop on Interactive Data Exploration and Analytics (IDEA’15), 13. Aug. 2015, Sydney

Zitieren

ISO 690

KWON, Bum Chul, Jaegul CHOO, Sung-Hee KIM, Daniel A. KEIM, Haesun PARK, Ji Soo YI, 2015. Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web. KDD 2015 Workshop on Interactive Data Exploration and Analytics (IDEA’15). Sydney, 13. Aug. 2015. In: POLO CHAU, , ed. and others. Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics Permission. New York: ACM, 2015, pp. 47-55

BibTex

@inproceedings{Kwon2015Opini-32597,
  year={2015},
  title={Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web},
  url={http://poloclub.gatech.edu/idea2015/papers/p47-kwon.pdf},
  publisher={ACM},
  address={New York},
  booktitle={Proceedings of the ACM SIGKDD Workshop on Interactive Data Exploration and Analytics Permission},
  pages={47--55},
  editor={Polo Chau},
  author={Kwon, Bum Chul and Choo, Jaegul and Kim, Sung-Hee and Keim, Daniel A. and Park, Haesun and Yi, Ji Soo}
}

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/123456789/32597">
    <dcterms:title>Opinion Marks : A Human-Based Computation Approach to Instill Structure into Unstructured Text on the Web</dcterms:title>
    <dc:creator>Keim, Daniel A.</dc:creator>
    <dc:rights>terms-of-use</dc:rights>
    <dc:contributor>Yi, Ji Soo</dc:contributor>
    <dc:creator>Park, Haesun</dc:creator>
    <dc:creator>Choo, Jaegul</dc:creator>
    <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-01-15T08:33:21Z</dcterms:available>
    <dc:contributor>Choo, Jaegul</dc:contributor>
    <dc:contributor>Kim, Sung-Hee</dc:contributor>
    <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dc:creator>Kim, Sung-Hee</dc:creator>
    <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/32597/1/Kwon_0-301049.pdf"/>
    <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2016-01-15T08:33:21Z</dc:date>
    <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/server/rdf/resource/123456789/36"/>
    <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/32597/1/Kwon_0-301049.pdf"/>
    <dcterms:rights rdf:resource="https://rightsstatements.org/page/InC/1.0/"/>
    <dc:contributor>Kwon, Bum Chul</dc:contributor>
    <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/>
    <dcterms:issued>2015</dcterms:issued>
    <dc:language>eng</dc:language>
    <dcterms:abstract xml:lang="eng">Despite recent improvements in computational approaches such as&lt;br /&gt;machine learning, natural language processing, and computational&lt;br /&gt;linguistics, making a computer understand human-generated unstructured&lt;br /&gt;text still remains a difficult problem to solve. To alleviate&lt;br /&gt;the challenges, we propose an approach called “Opinion Marks,”&lt;br /&gt;which enables writers to mark positive and negative aspects of a&lt;br /&gt;topic on their own text. In addition, Opinion Marks incorporates an&lt;br /&gt;automatic marking suggestion algorithm to offload a user’s marking&lt;br /&gt;effort. The phrases marked with Opinion Marks can be further&lt;br /&gt;used to clarify the sentiments of other text in a similar context.&lt;br /&gt;We implemented Opinion Marks at a question answering website&lt;br /&gt;http://caniask.net. To test the efficacy of Opinion Marks, we&lt;br /&gt;conducted a crowdsourced experiment with 144 participants in a&lt;br /&gt;between-subject design under three different conditions: 1) human&lt;br /&gt;marking only; 2) machine marking only (automatic marking suggestion);&lt;br /&gt;and 3) human-machine collaboration (Opinion Marks).&lt;br /&gt;This study revealed that Opinion Marks significantly improves the&lt;br /&gt;quality of marked phrases and usability of the system.</dcterms:abstract>
    <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/32597"/>
    <foaf:homepage rdf:resource="http://localhost:8080/"/>
    <dc:creator>Kwon, Bum Chul</dc:creator>
    <dc:creator>Yi, Ji Soo</dc:creator>
    <dc:contributor>Park, Haesun</dc:contributor>
    <dc:contributor>Keim, Daniel A.</dc:contributor>
  </rdf:Description>
</rdf:RDF>

URL der Originalveröffentl.

http://poloclub.gatech.edu/idea2015/papers/p47-kwon.pdf

Prüfdatum der URL

2016-01-15

Universitätsbibliographie

Ja