Recommender Systems Fairness Evaluation via Generalized Cross Entropy
This work addresses fairness evaluation for recommender systems, offering a novel perspective that could impact developers and researchers, though it appears incremental as it builds on existing fairness concepts with a new evaluation method.
The paper tackles the problem of fairness evaluation in recommender systems by arguing that fairness should consider resource distribution based on merits and needs rather than equality, and it presents a probabilistic framework using generalized cross entropy that shows flexibility and explanatory power on two real-world datasets.
Fairness in recommender systems has been considered with respect to sensitive attributes of users (e.g., gender, race) or items (e.g., revenue in a multistakeholder setting). Regardless, the concept has been commonly interpreted as some form of equality -- i.e., the degree to which the system is meeting the information needs of all its users in an equal sense. In this paper, we argue that fairness in recommender systems does not necessarily imply equality, but instead it should consider a distribution of resources based on merits and needs. We present a probabilistic framework based on generalized cross entropy to evaluate fairness of recommender systems under this perspective, where we show that the proposed framework is flexible and explanatory by allowing to incorporate domain knowledge (through an ideal fair distribution) that can help to understand which item or user aspects a recommendation algorithm is over- or under-representing. Results on two real-world datasets show the merits of the proposed evaluation framework both in terms of user and item fairness.