Recommender systems may enhance the discovery of novelties

2023/12/14 by De Marzo, Giordano, Gravino, Pietro, Loreto, Vittorio · 1 citation
#FOS: Physical sciences #Physics and Society (physics.soc-ph)

paper · doi:10.48550/arxiv.2312.08824

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.

Cited by

• 5 years of Journal of Physics: Complexity

Related

• An Empirical Analysis on Transparent Algorithmic Exploration in Recommender Systems
• One Size Does Not Fit All: Modeling Users' Personal Curiosity in Recommender Systems
• Beyond Relevance: An Adaptive Exploration-Based Framework for Personalized Recommendations
• The closed loop between opinion formation and personalised recommendations
• User-Creator Feature Polarization in Recommender Systems with Dual Influence