Gender In Gender Out: A Closer Look at User Attributes in Context-Aware Recommendation

TL;DR

This paper critically examines the role of user attributes in context-aware recommender systems, revealing their limited or negative impact on diversity and coverage, and exploring the privacy implications of user information in recommendations.

Contribution

It provides an empirical analysis showing that user attributes do not always enhance recommendations and can harm diversity and coverage, highlighting privacy concerns.

Findings

User attributes do not always improve recommendations.

User attributes can negatively affect diversity and coverage.

Information about users can leak into recommendation outputs.

Abstract

This paper studies user attributes in light of current concerns in the recommender system community: diversity, coverage, calibration, and data minimization. In experiments with a conventional context-aware recommender system that leverages side information, we show that user attributes do not always improve recommendation. Then, we demonstrate that user attributes can negatively impact diversity and coverage. Finally, we investigate the amount of information about users that ``survives'' from the training data into the recommendation lists produced by the recommender. This information is a weak signal that could in the future be exploited for calibration or studied further as a privacy leak.