Building Human Values into Recommender Systems: An Interdisciplinary Synthesis and Open Problems
Recommender systems are the algorithms which select, filter, and personalize content across many of the world’s largest platforms and apps. As such, their positive and negative effects on individuals and on societies have been extensively theorized and studied. The overarching question that arises is whether recommender systems align with the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and their practice, but critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy and law. This paper is a multidisciplinary effort to define a common language for addressing questions around human-value alignment for recommender systems, to synthesize the state of practice and insights from different perspectives, and to propose open problems. We propose a set of values that seem most relevant to recommender systems operating across different domains. We look at values from three different perspectives: 1) measurement, which is a key element of operationalizing values, 2) design, reflecting current approaches and open challenges to implementing these values, and 3) policy, the regulatory approaches which could provide appropriate incentives and standards for recommender system operators.