The Dynamics of Exploration on Spotify

Abstract

Digital media platforms give users access to enormous amounts of content that they must explore to avoid boredom and satisfy their needs for heterogeneity. Existing strands of work across psychology, marketing, computer science, and music underscore the importance of the lifecycle to understanding exploratory behavior, but they are also often inconsistent with each other. In this study, we examine how users explore online content on Spotify over time, 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 unknown content less and exploiting known content more. Across their on-platform histories, users also explore in bursts by following seasonal cycles and exploratory phases. We also find that these patterns of exploration do not translate to other notions of heterogeneity like diversity; notably, younger listeners are more diverse in their consumption despite exploring less. Exploration and diversity thus capture different ways in which people find variety, potentially accounting for the inconsistencies in existing work. Together, these nuanced dynamics of exploration suggest that online platforms may be better poised to support users by incorporating different measures of heterogeneous consumption.

The Analysis of the Future Hold of Spotify Technology S.A.

“…Spotify and Apple Music's different exclusive content and multimedia experience can also be one of the ways to analyze why Spotify is successful in the market. First, Spotify has chosen to sign many well-known bloggers and creators, completing the transition from its own music streaming platform to a multimedia entertainment platform [14]. This exclusive content encompasses audio from podcast authors from around the globe, which allows users to enjoy a wide range of genres in addition to music on the same platform [15].…”

Tracing the mechanisms of cultural diversity through 2.5 million individuals’ music listening patterns

“…While previous studies were limited to measuring diversity at the population scales (equivalent to our assessment of BID), we further leverage the individual-level data to understand how an individual's breadth of music engagement may be associated with the size of the region they reside in. To assess within-individual diversity (WID), we adopt a metric known as the Generalist-Specialist Score (GS-Score) of music engagement 42,43 by tracing each individual's past 28 days of listening history ( Measuring diversity in Methods). The GS-Score calculation is similar to our approach for assessing regional user dispersion in the previous section, but with a key distinction: we now measure the dispersion across songs within individual users' listening habits, rather than the dispersion among users.…”

“…When compared across the regional NUTS3 population of France, strong correlations were observed between the number of users and census population size (r = 0.90, p < .001), and their median age (r = 0.61, p < .001). However, when stratified by age groups, our user sample consisted of 25% more young (between ages 15-30), 3% more mid-age (31)(32)(33)(34)(35)(36)(37)(38)(39)(40)(41)(42)(43)(44)(45)(46)(47)(48)(49)(50), and 30% less elderly (51-80) populations. Our sample demonstrated a slightly skewed tendency towards having more male demographics (52% male) compared to France's general population (48% male).…”

“…To assess an individual's diversity of musical engagement, we employed the Generalist-Specialist Score (GS-Score), a previously validated metric in user music exploration and discovery studies 42,43 . The GS-Score of a user ( u ) is computed by taking the cosine similarity between a given user's mean vector , calculated from all the songs the user consumed within the last 28 days, and the vector representation of a randomly selected song ( ) they have listened to, weighted by the number of times they have listened ( w s ).…”

“…Studies have shown how one's musical exploration 43 and preferences 45 are influenced by age, demonstrating that one's music taste generally consolidates during adolescence. Recent studies have also shown significant differences between the consumption patterns of males and females 46,73 .…”