Reproduce “Recommending Podcasts for Cold-Start Users Based on Music Listening and Taste” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zahra Nazari, Christophe Charbuillet, Johan Pages, Martin Laurent, Denis Charrier, Briana Vecchione, Ben Carterette
The authors rank podcasts for Spotify users without podcast histories using demographics, music-based collaborative filtering, and metadata. In a one-week test with 800,000 users, treatment users listened to nearly 50% more podcast minutes and followed over 50% more shows than users given a popularity-based slate. This result applies to Spotify users with music histories and no prior podcast use.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.