A survey on popularity bias in recommender systems

• DOI: 10.1007/s11257-024-09406-0
• Publication Date: 2024-07-02T04:58:27Z
• Authors: Anastasiia Klimas...; Dietmar Jannach; Mehdi Elahi; Christoph Trattner
• Keywords: Popularity; Visibility; Value (mathematics)

Abstract Recommender systems help people find relevant content in a personalized way. One main promise of such is that they are able to increase the visibility items long tail , i.e., lesser-known catalogue. Existing research, however, suggests many situations today’s recommendation algorithms instead exhibit popularity bias meaning often focus on rather popular their recommendations. Such may not only lead limited value recommendations for consumers and providers short run, but it also cause undesired reinforcement effects over time. In this paper, we discuss potential reasons review existing approaches detect, quantify mitigate recommender systems. Our survey, therefore, includes both an overview computational metrics used literature as well technical reduce bias. Furthermore, critically literature, where observe research almost entirely based experiments certain assumptions regarding practical including long-tail