PodRecs: Workshop on Podcast Recommendations @ ACM RecSys



**Due to concerns about COVID-19, RecSys 2020 has canceled its physical component, and will take place fully online from Sept 22-26, 2020. The submission deadline has been extended to July 29th to allow authors more time to prepare their papers. **


=========

Description

=========


The last year has been a breakout year for podcasts. There are now over 1 million podcast shows and over 64 million podcast episodes available through public RSS feeds. In the United States, 32% of all people listened to a podcast every month, and forecasts point to global podcast listenership to reach 2.2 billion monthly listeners by 2024. 


As a media type, Podcasts are familiar, yet unique: while they are a recorded audio format like music, their content is much broader, and more akin to television, news, books, and radio. The variety of podcast subjects is vast, and covers news, sports, comedy, fictional narrative, financial, technology, political commentary, and more. Podcast listening patterns also differ from music: they require longer, more dedicated listening time, and the release cadence is usually much more frequent (daily, weekly) than music.


For those reasons, we believe that existing recommender system techniques and approaches require novel ways of thinking about podcasts and how to recommend them to listeners. The workshop on Podcast Recommendations (PodRecs), collocated with RecSys 2020, will introduce researchers in other domains of recommender systems to the special characteristics and challenges of podcast recommendations, as well as showcase the leading research being done in this area. 


=============

Topics of Interest

=============


Topics of interest for the workshop include, but are not limited to, the following:


- Data mining from podcast episode transcripts

- Knowledge mining/knowledge graphs on podcast shows and episodes

- Search in podcast transcripts

- Content-based podcast show and episode recommendation

- Collaborative filtering / interaction based podcast show and episode recommendation

- Transfer learning and podcast recommendation 

- Podcast audio signal processing and speech recognition

- User preference elicitation for podcasts

- User studies of podcast listening

- Mixed level recommendation (recommending series, episodes, and episode segments in one stream. Utility of mixed-level recommendations.  Methods of doing mixed-level recommendation)

- Misinformation/disinformation and the spoken word

- Combining human and automatic recommendations for podcasts

- Fairness: Balancing established and emerging podcasters, mainstream and independent voices, diversity in languages, etc

- Cross-references: Handling mentions of other podcasts from within podcasts

- Explanations: Why is this content being recommended?

- Voice-interface and conversational recommendation for podcasts

- Podcast discovery

- Evaluation methodology

- Podcast ranking, learning to rank

- Item cold start problem in podcasts

- Habitual aspects of podcast recommendations

- Contextual aspects of podcast recommendations


Authors are encouraged to submit position papers, as well as ongoing or recent research related to topics of interests. The workshop program committee will consider all submitted papers and will decide which papers are to be presented as oral or poster presentations. We offer authors the choice of archival and non-archival paper submissions.  The non-archival option is to avoid precluding the future submission of these papers to other venues. Moreover, submissions to the workshop based on recently published work are also acceptable (though authors should explicitly make note of this in their submissions). 


===============

Submission Format

===============


Submitted paper should be between 6-8 pages long (not including references). Submissions are not blind: author names and affiliations should appear on the first page. Papers should be formatted using the ACM Master Article Template. For LaTeX users, You must use the “manuscript” option with the \documentclass[manuscript]{acmart} command to generate the output in a single-column format which is required for review. This is the new, single-column proceedings-style template. Authors do not need to include terms, keywords, or other front matter in their submissions.


==============

Workshop Website

==============

https://sites.google.com/view/podrecs2020 


============

Submission Site

============

https://easychair.org/conferences/?conf=podrecs2020 


========

Key Dates

========

(All deadlines in AoE time zone)

Submission deadline: Jul 13th Jul 29th

Reviews due: July 31st Aug 14th

Author notification: Aug 6th Aug 21st

Camera-ready deadline (for archival submissions): Sept 3rd Sept 4th

Workshop date: Sept 25th


=========

Organizers

=========

Ching-Wei Chen, Spotify

Longqi Yang, Microsoft

Hongyi Wen, Cornell Tech

Rosie Jones, Spotify

Vladan Radosavljevic, Spotify

Hugues Bouchard, Spotify


For more updates, please follow us on Twitter: https://www.twitter.com/podrecsys

Comments