Investigating the impact of recommender systems on user-based and item-based popularity bias

作者：

Highlights：

• We measure reinforced recommendation-driven popularity bias on several algorithms.

• We compare bias reinforcement on datasets and show how it is reinforced differently.

• We show algorithms increase bias at the user level but decrease it at the item level.

• We show the differences of the algorithms affecting the bias on the language basis.

摘要

•We measure reinforced recommendation-driven popularity bias on several algorithms.•We compare bias reinforcement on datasets and show how it is reinforced differently.•We show algorithms increase bias at the user level but decrease it at the item level.•We show the differences of the algorithms affecting the bias on the language basis.

论文关键词：Recommender systems,Popularity bias,Personalization,Twitter,Social media

论文评审过程：Received 30 November 2020, Revised 17 May 2021, Accepted 26 May 2021, Available online 16 June 2021, Version of Record 16 June 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102655