Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Tracing Affordance and Item Adoption on Music Streaming Platforms

Dougal Shakespeare, Camille Roth

TL;DR

This study investigates how users adopt platform affordances $O$, $A$, and $E$ and how items are adopted within those affordances on a music streaming platform, using ~2 years of Deezer listening data. It introduces an adoption metric framework, including $\alpha_F$ and $\alpha'_F$, and identifies four affordance-adoption classes via clustering of user profiles, revealing substantial heterogeneity in behavior. Temporal analysis shows time-of-day patterns shape low-level activity, while affordance adoption strongly mediates higher-level item adoption and catalog composition, challenging the notion of a uniform organic baseline. The findings offer implications for context-aware recommender systems and platform design that accommodate diverse user strategies for exploring and adopting content.

Abstract

Popular music streaming platforms offer users a diverse network of content exploration through a triad of affordances: organic, algorithmic and editorial access modes. Whilst offering great potential for discovery, such platform developments also pose the modern user with daily adoption decisions on two fronts: platform affordance adoption and the adoption of recommendations therein. Following a carefully constrained set of Deezer users over a 2-year observation period, our work explores factors driving user behaviour in the broad sense, by differentiating users on the basis of their temporal daily usage, adoption of the main platform affordances, and the ways in which they react to them, especially in terms of recommendation adoption. Diverging from a perspective common in studies on the effects of recommendation, we assume and confirm that users exhibit very diverse behaviours in using and adopting the platform affordances. The resulting complex and quite heterogeneous picture demonstrates that there is no blanket answer for adoption practices of both recommendation features and recommendations.

Tracing Affordance and Item Adoption on Music Streaming Platforms

TL;DR

This study investigates how users adopt platform affordances , , and and how items are adopted within those affordances on a music streaming platform, using ~2 years of Deezer listening data. It introduces an adoption metric framework, including and , and identifies four affordance-adoption classes via clustering of user profiles, revealing substantial heterogeneity in behavior. Temporal analysis shows time-of-day patterns shape low-level activity, while affordance adoption strongly mediates higher-level item adoption and catalog composition, challenging the notion of a uniform organic baseline. The findings offer implications for context-aware recommender systems and platform design that accommodate diverse user strategies for exploring and adopting content.

Abstract

Popular music streaming platforms offer users a diverse network of content exploration through a triad of affordances: organic, algorithmic and editorial access modes. Whilst offering great potential for discovery, such platform developments also pose the modern user with daily adoption decisions on two fronts: platform affordance adoption and the adoption of recommendations therein. Following a carefully constrained set of Deezer users over a 2-year observation period, our work explores factors driving user behaviour in the broad sense, by differentiating users on the basis of their temporal daily usage, adoption of the main platform affordances, and the ways in which they react to them, especially in terms of recommendation adoption. Diverging from a perspective common in studies on the effects of recommendation, we assume and confirm that users exhibit very diverse behaviours in using and adopting the platform affordances. The resulting complex and quite heterogeneous picture demonstrates that there is no blanket answer for adoption practices of both recommendation features and recommendations.

Paper Structure

This paper contains 11 sections, 8 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Appraising Algorithmic Influence via an Organic Comparison
  4. Item Adoption in Recommender System
  5. Temporal Dimensions of mRS Usage
  6. Methodology
  7. Listening Events Data Set
  8. Defining user classes
  9. Item Adoption
  10. Results
  11. Concluding remarks

Figures (5)

  • Figure 1: Ternary plot of affordance adoption classes ø+ (blue), o (grey), e (green), a (purple), disks represent centroid positions. Crosses represent corrected centroid positions after taking into account the pre-adoption origin of plays (see Sec. \ref{['sec:discussion']}).
  • Figure 2: Normalised platform affordance time-of-day activity. Aggregate levels are shown (top) followed by z-normalised activity (middle) and residual de-trended activity levels (bottom).
  • Figure 3: Normalised time-of-day activity levels for each time-of-day class. Aggregate levels are shown (top) followed by residual de-trended activity levels (bottom).
  • Figure 4: Affordance vs. time-of-day distributions. Values are normalised such that above or below 1 indicate respectively similar, over- or under- representation of affordance classes respective to those found globally.
  • Figure :