Measuring and mitigating biases in location-based recommender systems

Abstract

This article is a summary of the work published in the journal Data Mining and Knowledge Discovery[1]. It presents an analysis of different types of biases and polarization measurements that affect the area of Point-Of-Interest recommendation. Our results evidence which state-of-the-art recommender ssuffer from popularity bias,venue exposure polarization,and geograph-ical distance polarization.This article is a summary of the work published in the journal Data Mining and Knowledge Discovery[1]. It presents an analysis of different types of biases and polarization measurements that affect the area of Point-Of-Interest recommendation. Our results evidence which state-of-the-art recommender ssuffer from popularity bias,venue exposure polarization,and geograph-ical distance polarization.