Podcast Metadata and Content: Episode Relevance and Attractiveness in Ad Hoc Search

Rapidly growing online podcast archives contain diverse content on a wide range of topics. These archives form an important resource for entertainment and professional use, but their value can only be realized if users can rapidly and reliably locate content of interest. Search for relevant content can be based on metadata provided by content creators, but also on transcripts of the spoken content itself. Excavating relevant content from deep within these audio streams for diverse types of information needs requires varying the approach to systems prototyping. We describe a set of diverse podcast information needs and different approaches to assessing retrieved content for relevance. We use these information needs in an investigation of the utility and effectiveness of these information sources. Based on our analysis, we recommend approaches for indexing and retrieving podcast content for ad hoc search.

[1]  W. Bruce Croft,et al.  A Field Relevance Model for Structured Document Retrieval , 2012, ECIR.

[2]  Maria Eskevich,et al.  SAVA at MediaEval 2015: Search and Anchoring in Video Archives , 2015, MediaEval.

[3]  Gareth J. F. Jones,et al.  Overview of the NTCIR-12 SpokenQuery&Doc-2 Task , 2016, NTCIR.

[4]  Bhaskar Mitra,et al.  Neural Ranking Models with Multiple Document Fields , 2017, WSDM.

[5]  Thorsten Joachims,et al.  Estimating Position Bias without Intrusive Interventions , 2018, WSDM.

[6]  Martha Larson,et al.  Overview of MediaEval 2011 Rich Speech Retrieval Task and Genre Tagging Task , 2011, MediaEval.

[7]  Martha Larson,et al.  Search and Hyperlinking Task at MediaEval 2012 , 2012, MediaEval.

[8]  Stephen E. Robertson,et al.  Simple BM25 extension to multiple weighted fields , 2004, CIKM '04.

[9]  Ellen M. Voorhees,et al.  Variations in relevance judgments and the measurement of retrieval effectiveness , 1998, SIGIR '98.

[10]  M. de Rijke,et al.  PodCred: a framework for analyzing podcast preference , 2008, WICOW '08.

[11]  Michael Eisenberg,et al.  Order effects: A study of the possible influence of presentation order on user judgments of document relevance , 1988, J. Am. Soc. Inf. Sci..

[12]  Matthew Sharpe.  A review of metadata fields associated with podcast RSS feeds , 2020, ArXiv.

[13]  Ben Carterette,et al.  100,000 Podcasts: A Spoken English Document Corpus , 2020, COLING.

[14]  Mark Sanderson,et al.  Extracting audio summaries to support effective spoken document search , 2017, J. Assoc. Inf. Sci. Technol..

[15]  Mounia Lalmas,et al.  Evaluating XML retrieval effectiveness at INEX , 2007, SIGF.

[16]  Gabriella Kazai,et al.  Advances in XML Information Retrieval and Evaluation, 4th International Workshop of the Initiative for the Evaluation of XML Retrieval, INEX 2005, Dagstuhl Castle, Germany, November 28-30, 2005, Revised Selected Papers , 2006, INEX.

[17]  Ellen M. Voorhees,et al.  The TREC Spoken Document Retrieval Track: A Success Story , 2000, TREC.

[18]  Ryen W. White,et al.  Overview of the CLEF-2005 Cross-Language Speech Retrieval Track , 2005, CLEF.

[19]  Gareth J. F. Jones,et al.  Overview of the CLEF-2005 Cross-Language Speech Retrieval Track , 2005, CLEF.

[20]  M. D. Rijke,et al.  Information Retrieval Evaluation in a Changing World: Lessons Learned from 20 Years of CLEF , 2019, Information Retrieval Evaluation in a Changing World.

[21]  Katja Hofmann,et al.  An Exploratory Study of User Goals and Strategies in Podcast Search , 2008, LWA.