The reinforcing influence of recommendations on global diversification

TL;DR

This paper investigates how different recommender system algorithms influence the distribution of item popularity, revealing that some algorithms reinforce popular items while others promote niche items, affecting global diversification.

Contribution

It provides a comparative analysis of recommender algorithms' effects on item popularity dispersion using simulations and mean-field predictions.

Findings

Collaborative filtering reinforces popular items, increasing dispersion.

Heat conduction algorithm promotes niche items, reducing dispersion.

Recommender systems can either reinforce or diversify item popularity.

Abstract

Recommender systems are promising ways to filter the overabundant information in modern society. Their algorithms help individuals to explore decent items, but it is unclear how they allocate popularity among items. In this paper, we simulate successive recommendations and measure their influence on the dispersion of item popularity by Gini coefficient. Our result indicates that local diffusion and collaborative filtering reinforce the popularity of hot items, widening the popularity dispersion. On the other hand, the heat conduction algorithm increases the popularity of the niche items and generates smaller dispersion of item popularity. Simulations are compared to mean-field predictions. Our results suggest that recommender systems have reinforcing influence on global diversification.