Gender In Gender Out: A Closer Look at User Attributes in Context-Aware Recommendation
This work addresses concerns in recommender systems for users and developers regarding fairness and privacy, though it is incremental as it builds on existing context-aware methods.
The paper investigates the impact of user attributes on context-aware recommender systems, finding that they do not consistently improve recommendations and can harm diversity and coverage, while also revealing a weak signal of user information in outputs that could be exploited for calibration or pose privacy risks.
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.