Predicting podcast preference: An analysis framework and its application
Identifieur interne : 000422 ( Main/Exploration ); précédent : 000421; suivant : 000423Predicting podcast preference: An analysis framework and its application
Auteurs : Manos Tsagkias [Pays-Bas] ; Martha Larson [Pays-Bas] ; Maarten De Rijke [Pays-Bas]Source :
- Journal of the American Society for Information Science and Technology [ 1532-2882 ] ; 2010-02.
English descriptors
- Teeft :
- American society, Audio, Baseline, Basic system, Bayes, Blog, Cfssubset, Credibility, Cumulative features, Data analysis, Dataset, Encode, Exploratory investigation, Feature sets, Framework, Gain ratio, Genre, Guideline, Human analysis, Indicator, Information gain, Information science, Internet, Itunes, Liddy, Logo, Metadata, Metzger, Multimedia, Naive bayes, Nonpreferred, Online, Optimized, Podcast, Podcast content, Podcast episodes, Podcast feed, Podcast preference, Podcaster, Podcasters, Podcasting, Podcasts, Podcred, Podcred framework, Podosphere, Prescriptive, Prescriptive guidelines, Randomforest, Retrieval, Rieh, Rijke, Rubin, Rubin liddy, Snapshot, Snapshot features, Support vector machine, Surface features, Topical focus, Tsagkias, User, User perceptions, Validation, Validation exercise.
Abstract
Finding worthwhile podcasts can be difficult for listeners since podcasts are published in large numbers and vary widely with respect to quality and repute. Independently of their informational content, certain podcasts provide satisfying listening material while other podcasts have little or no appeal. In this paper we present PodCred, a framework for analyzing listener appeal, and we demonstrate its application to the task of automatically predicting the listening preferences of users. First, we describe the PodCred framework, which consists of an inventory of factors contributing to user perceptions of the credibility and quality of podcasts. The framework is designed to support automatic prediction of whether or not a particular podcast will enjoy listener preference. It consists of four categories of indicators related to the Podcast Content, the Podcaster, the Podcast Context, and the Technical Execution of the podcast. Three studies contributed to the development of the PodCred framework: a review of the literature on credibility for other media, a survey of prescriptive guidelines for podcasting, and a detailed data analysis. Next, we report on a validation exercise in which the PodCred framework is applied to a real‐world podcast preference prediction task. Our validation focuses on select framework indicators that show promise of being both discriminative and readily accessible. We translate these indicators into a set of easily extractable “surface” features and use them to implement a basic classification system. The experiments carried out to evaluate system use popularity levels in iTunes as ground truth and demonstrate that simple surface features derived from the PodCred framework are indeed useful for classifying podcasts.
Url:
DOI: 10.1002/asi.21259
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000492
- to stream Istex, to step Curation: 000465
- to stream Istex, to step Checkpoint: 000275
- to stream Main, to step Merge: 000422
- to stream Main, to step Curation: 000422
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Predicting podcast preference: An analysis framework and its application</title><author><name sortKey="Tsagkias, Manos" sort="Tsagkias, Manos" uniqKey="Tsagkias M" first="Manos" last="Tsagkias">Manos Tsagkias</name></author><author><name sortKey="Larson, Martha" sort="Larson, Martha" uniqKey="Larson M" first="Martha" last="Larson">Martha Larson</name></author><author><name sortKey="De Rijke, Maarten" sort="De Rijke, Maarten" uniqKey="De Rijke M" first="Maarten" last="De Rijke">Maarten De Rijke</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:2FBECB208C70ABB8A921F0481435AE7C23B1B8E5</idno><date when="2010" year="2010">2010</date><idno type="doi">10.1002/asi.21259</idno><idno type="url">https://api.istex.fr/document/2FBECB208C70ABB8A921F0481435AE7C23B1B8E5/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">000492</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000492</idno><idno type="wicri:Area/Istex/Curation">000465</idno><idno type="wicri:Area/Istex/Checkpoint">000275</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000275</idno><idno type="wicri:doubleKey">1532-2882:2010:Tsagkias M:predicting:podcast:preference</idno><idno type="wicri:Area/Main/Merge">000422</idno><idno type="wicri:Area/Main/Curation">000422</idno><idno type="wicri:Area/Main/Exploration">000422</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Predicting podcast preference: An analysis framework and its application</title><author><name sortKey="Tsagkias, Manos" sort="Tsagkias, Manos" uniqKey="Tsagkias M" first="Manos" last="Tsagkias">Manos Tsagkias</name><affiliation wicri:level="4"><country xml:lang="fr">Pays-Bas</country><wicri:regionArea>ISLA, University of Amsterdam, Science Park 107, Amsterdam</wicri:regionArea><placeName><settlement type="city">Amsterdam</settlement><region nuts="2" type="province">Hollande-Septentrionale</region></placeName><orgName type="university">Université d'Amsterdam</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Pays-Bas</country></affiliation></author><author><name sortKey="Larson, Martha" sort="Larson, Martha" uniqKey="Larson M" first="Martha" last="Larson">Martha Larson</name><affiliation wicri:level="1"><country xml:lang="fr">Pays-Bas</country><wicri:regionArea>EEMCS, Delft University of Technology, Delft</wicri:regionArea><wicri:noRegion>Delft</wicri:noRegion></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Pays-Bas</country></affiliation></author><author><name sortKey="De Rijke, Maarten" sort="De Rijke, Maarten" uniqKey="De Rijke M" first="Maarten" last="De Rijke">Maarten De Rijke</name><affiliation wicri:level="4"><country xml:lang="fr">Pays-Bas</country><wicri:regionArea>ISLA, University of Amsterdam, Science Park 107, Amsterdam</wicri:regionArea><placeName><settlement type="city">Amsterdam</settlement><region nuts="2" type="province">Hollande-Septentrionale</region></placeName><orgName type="university">Université d'Amsterdam</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Pays-Bas</country></affiliation></author></analytic><monogr></monogr><series><title level="j">Journal of the American Society for Information Science and Technology</title><title level="j" type="abbrev">J. Am. Soc. Inf. Sci.</title><idno type="ISSN">1532-2882</idno><idno type="eISSN">1532-2890</idno><imprint><publisher>Wiley Subscription Services, Inc., A Wiley Company</publisher><pubPlace>Hoboken</pubPlace><date type="published" when="2010-02">2010-02</date><biblScope unit="volume">61</biblScope><biblScope unit="issue">2</biblScope><biblScope unit="page" from="374">374</biblScope><biblScope unit="page" to="391">391</biblScope></imprint><idno type="ISSN">1532-2882</idno></series><idno type="istex">2FBECB208C70ABB8A921F0481435AE7C23B1B8E5</idno><idno type="DOI">10.1002/asi.21259</idno><idno type="ArticleID">ASI21259</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1532-2882</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="Teeft" xml:lang="en"><term>American society</term><term>Audio</term><term>Baseline</term><term>Basic system</term><term>Bayes</term><term>Blog</term><term>Cfssubset</term><term>Credibility</term><term>Cumulative features</term><term>Data analysis</term><term>Dataset</term><term>Encode</term><term>Exploratory investigation</term><term>Feature sets</term><term>Framework</term><term>Gain ratio</term><term>Genre</term><term>Guideline</term><term>Human analysis</term><term>Indicator</term><term>Information gain</term><term>Information science</term><term>Internet</term><term>Itunes</term><term>Liddy</term><term>Logo</term><term>Metadata</term><term>Metzger</term><term>Multimedia</term><term>Naive bayes</term><term>Nonpreferred</term><term>Online</term><term>Optimized</term><term>Podcast</term><term>Podcast content</term><term>Podcast episodes</term><term>Podcast feed</term><term>Podcast preference</term><term>Podcaster</term><term>Podcasters</term><term>Podcasting</term><term>Podcasts</term><term>Podcred</term><term>Podcred framework</term><term>Podosphere</term><term>Prescriptive</term><term>Prescriptive guidelines</term><term>Randomforest</term><term>Retrieval</term><term>Rieh</term><term>Rijke</term><term>Rubin</term><term>Rubin liddy</term><term>Snapshot</term><term>Snapshot features</term><term>Support vector machine</term><term>Surface features</term><term>Topical focus</term><term>Tsagkias</term><term>User</term><term>User perceptions</term><term>Validation</term><term>Validation exercise</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Finding worthwhile podcasts can be difficult for listeners since podcasts are published in large numbers and vary widely with respect to quality and repute. Independently of their informational content, certain podcasts provide satisfying listening material while other podcasts have little or no appeal. In this paper we present PodCred, a framework for analyzing listener appeal, and we demonstrate its application to the task of automatically predicting the listening preferences of users. First, we describe the PodCred framework, which consists of an inventory of factors contributing to user perceptions of the credibility and quality of podcasts. The framework is designed to support automatic prediction of whether or not a particular podcast will enjoy listener preference. It consists of four categories of indicators related to the Podcast Content, the Podcaster, the Podcast Context, and the Technical Execution of the podcast. Three studies contributed to the development of the PodCred framework: a review of the literature on credibility for other media, a survey of prescriptive guidelines for podcasting, and a detailed data analysis. Next, we report on a validation exercise in which the PodCred framework is applied to a real‐world podcast preference prediction task. Our validation focuses on select framework indicators that show promise of being both discriminative and readily accessible. We translate these indicators into a set of easily extractable “surface” features and use them to implement a basic classification system. The experiments carried out to evaluate system use popularity levels in iTunes as ground truth and demonstrate that simple surface features derived from the PodCred framework are indeed useful for classifying podcasts.</div></front></TEI><affiliations><list><country><li>Pays-Bas</li></country><region><li>Hollande-Septentrionale</li></region><settlement><li>Amsterdam</li></settlement><orgName><li>Université d'Amsterdam</li></orgName></list><tree><country name="Pays-Bas"><region name="Hollande-Septentrionale"><name sortKey="Tsagkias, Manos" sort="Tsagkias, Manos" uniqKey="Tsagkias M" first="Manos" last="Tsagkias">Manos Tsagkias</name></region><name sortKey="De Rijke, Maarten" sort="De Rijke, Maarten" uniqKey="De Rijke M" first="Maarten" last="De Rijke">Maarten De Rijke</name><name sortKey="De Rijke, Maarten" sort="De Rijke, Maarten" uniqKey="De Rijke M" first="Maarten" last="De Rijke">Maarten De Rijke</name><name sortKey="Larson, Martha" sort="Larson, Martha" uniqKey="Larson M" first="Martha" last="Larson">Martha Larson</name><name sortKey="Larson, Martha" sort="Larson, Martha" uniqKey="Larson M" first="Martha" last="Larson">Martha Larson</name><name sortKey="Tsagkias, Manos" sort="Tsagkias, Manos" uniqKey="Tsagkias M" first="Manos" last="Tsagkias">Manos Tsagkias</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sarre/explor/MusicSarreV3/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000422 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000422 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Sarre
|area= MusicSarreV3
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:2FBECB208C70ABB8A921F0481435AE7C23B1B8E5
|texte= Predicting podcast preference: An analysis framework and its application
}}
| This area was generated with Dilib version V0.6.33. |  |