Recommender systems may enhance the discovery of novelties

TL;DR

This paper presents a model showing that recommender systems can actually promote the discovery of new content, challenging the belief they limit exploration and increase polarization.

Contribution

The paper introduces a framework to analyze how recommender systems influence novelty discovery and opinion polarization, beyond traditional accuracy metrics.

Findings

Recommender systems can enhance novelty discovery rates.

Different algorithms with similar discovery rates can lead to different polarization outcomes.

The approach provides a new way to evaluate recommendation techniques.

Abstract

Recommender systems are vital for shaping user online experiences. While some believe they may limit new content exploration and promote opinion polarization, a systematic analysis is still lacking. We present a model that explores the influence of recommender systems on novel content discovery. Surprisingly, analytical and numerical findings reveal these techniques can enhance novelty discovery rates. Also, distinct algorithms with similar discovery rates yield varying opinion polarization outcomes. Our approach offers a framework to enhance recommendation techniques beyond accuracy metrics.