Exploring the Effect of Context-Awareness and Popularity Calibration on Popularity Bias in POI Recommendations

TL;DR

This paper investigates how context-awareness and popularity calibration techniques influence popularity bias in POI recommendation systems, finding that their combination can effectively balance recommendation accuracy with bias mitigation.

Contribution

It provides a comprehensive evaluation of context-aware and calibration methods, highlighting their individual and combined effects on reducing popularity bias in POI recommendations.

Findings

Context-aware models show divergent impacts on accuracy and bias.

Calibration techniques effectively align recommendations with user preferences.

Combining calibration with context-awareness balances accuracy and bias mitigation.

Abstract

Point-of-interest (POI) recommender systems help users discover relevant locations, but their effectiveness is often compromised by popularity bias, which disadvantages less popular, yet potentially meaningful places. This paper addresses this challenge by evaluating the effectiveness of context-aware models and calibrated popularity techniques as strategies for mitigating popularity bias. Using four real-world POI datasets (Brightkite, Foursquare, Gowalla, and Yelp), we analyze the individual and combined effects of these approaches on recommendation accuracy and popularity bias. Our results reveal that context-aware models cannot be considered a uniform solution, as the models studied exhibit divergent impacts on accuracy and bias. In contrast, calibration techniques can effectively align recommendation popularity with user preferences, provided there is a careful balance between accuracy and bias mitigation. Notably, the combination of calibration and context-awareness yields recommendations that balance accuracy and close alignment with the users' popularity profiles, i.e., popularity calibration.