Podcasts continue to enjoy impressive growth in both creation and listenership. As of Feb 2021 the podcast website Listen Notes reports over 1.9M podcast shows available through public RSS feeds - this figure is more than double the figure from just one year earlier. The Daily by The New York Times, is downloaded over 4 million times per day, double the rate reported a year ago. Edison Research’s Infinite Dial 2020 Report estimates that 37% of the US population had listened to a podcast in the last month, a significant increase from the 32% estimated in their 2019 report. A similar statistic from 2018 indicated that 28% of Europeans had listened to a podcast in the last month.
In addition, the recent rise of audio social media apps such as Clubhouse and Twitter’s Spaces has created a new momentum towards spoken word content. This movement can contribute to the growth of podcasts both in the number of audience and emerging creators as well as introducing new challenges to the field.
The last year has also seen increased research interest in this field. Besides the first PodRecs Workshop on Podcast Recommendations at RecSys 2020, we also saw the release of the Spotify Podcast Dataset in conjunction with NIST TREC, as well as the NLP4MusA Workshop at the ISMIR conference.
The Second PodRecs Workshop for Podcast Recommendations will be held in conjunction with RecSys 2021. This workshop will build off the success of last year’s workshop, and will seek to further develop the community of researchers and practitioners interested in the recommendation of podcasts. The programme will again include reviewed papers, a keynote, and an interactive activity for workshop attendees.
Topics of interest for the workshop include, but are not limited to, the following:
Processing and analysis of podcast content
Audio signal processing and speech recognition
Knowledge mining/knowledge graphs on podcast shows and episodes
Data mining from podcast episode transcripts
Cross-references: Handling mentions of other podcasts from within podcasts
Search and recommendation technology
Search in podcast using transcripts and other metadata
Content-based podcast show and episode recommendation
Podcast ranking, learning to rank
Item cold start problem in podcasts
Transfer learning and podcast recommendation
Combining human and automatic recommendations for podcasts
Collaborative filtering / interaction based podcast show and episode recommendation
Misinformation/disinformation and the spoken word
User studies
User preference elicitation for podcasts
User studies of podcast listening
Habitual aspects of podcast recommendations
Contextual aspects of podcast recommendations
Podcast discovery, access, and systems evaluation
Podcast discovery
Explanations: Why is this content being recommended?
Mixed level recommendation: recommending series, episodes, and episode segments in one stream. Utility of mixed-level recommendations. Methods of doing mixed-level recommendation)
Evaluation methodology for podcast search and recommendations
Fairness: Balancing established and emerging podcasters, mainstream and independent voices, diversity in languages, etc
Voice-interface and conversational recommendation for podcasts
Authors are encouraged to submit ongoing or recent research related to topics of interests. We offer authors the choice of archival and non-archival paper submissions. The non-archival option is to allow 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).
We are accepting submissions of full papers, which should be between 6-8 pages long (not including references). Please note: The new RecSys proceedings template is a single-column format. You can try out the template on Overleaf to estimate how long your paper will be.
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. Authors do not need to include terms, keywords, or other front matter in their submissions.
https://easychair.org/my/conference?conf=podrecs2021
(All deadlines in AoE time zone)
Paper submission deadline: July 29th, 2021
Reviewer deadline: August 14th, 2021
Author notification: August 21st, 2021
Camera-ready version deadline: September 4th, 2021