About this document

Popularity Bias in Recommender Systems by ceboc130 is a document available to read on EtoBox.

This study evaluates the popularity bias in recommender systems from a user-centric perspective, highlighting how popular items dominate recommendations while niche items are often overlooked, leading to unfairness for users. It identifies five key user characteristics that influence their interaction with recommendation algorithms and analyzes their correlation with popularity bias. The findings suggest that while some debiasing strategies improve fairness, they often compromise ranking accuracy, indicatin

Author

ceboc130

Language

EN