The Dynamics of Exploration on Spotify


Digital media platforms give users access to enormous amounts of content. To stay interested in this content, users must explore by seeking variety. In this study, we examine how users explore online content on Spotify at different points of their lifecycles, whether by discovering entirely novel music or by refreshing their listening habits from one time frame to the next. We find clear differences between users at different points of their off-platform lifecycles, with younger listeners consistently exploring less and exploiting known content more. Across their on-platform histories, users also explore in uneven patterns by following seasonal cycles and exploratory phases. Additionally, we contrast exploration with taste diversity and find that these concepts are surprisingly distinct. Through this large-scale, observational study of exploration, our work clarifies how users encounter and cycle through heterogeneous content at various stages of their lifecycle.


March 2023 | Frontier on Big Data: Recommender Systems

A Survey on Multi-objective Recommender Systems

Dietmar Jannach and Himan Abdollahpouri

March 2023 | Intelligent User Interfaces (IUI)

Enabling Goal-Focused Exploration of Podcasts in Interactive Recommender Systems

Yu Liang, Aditya Ponnada, Paul Lamere, Nediyana Daskalova

February 2023 | WSDM

Calibrated Recommendations as a Minimum-Cost Flow Problem

Himan Abdollahpouri, Zahra Nazari, Alex Gain,Clay Giibson, Maria Dimakopoulou, Jesse Anderton, Benjamin Carterette, Mounia Lalmas, Tony Jebara