Building Human Values into Recommender Systems: An Interdisciplinary Synthesis
Authors:
- Jonathan StrayJSJonathan Stray
- Alon HalevyAHAlon Halevy
- Parisa AssarPAParisa Assar
- Dylan Hadfield-MenellDHDylan Hadfield-Menell
- Craig BoutilierCBCraig Boutilier
- Amar AsharAAAmar Ashar
- Chloe BakalarCBChloe Bakalar
- Lex BeattieLBLex Beattie
- Michael EkstrandMEMichael Ekstrand
- Claire LeibowiczCLClaire Leibowicz
- Connie Moon SehatCSConnie Moon Sehat
- Sara JohansenSJSara Johansen
Top Cited Papers
Open Access
- 5 June 2024
- journal article
- research article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Recommender Systems
- Vol. 2 (3) , 1-57
Abstract
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. Our overarching question is how to ensure that recommender systems enact the values of the individuals and societies that they serve. Addressing this question in a principled fashion requires technical knowledge of recommender design and operation, and also critically depends on insights from diverse fields including social science, ethics, economics, psychology, policy, and law. This article is a multidisciplinary effort to synthesize theory and practice from different perspectives, with the goal of providing a shared language, articulating current design approaches, and identifying open problems. We collect a set of values that seem most relevant to recommender systems operating across different domains, and then examine them from the perspectives of current industry practice, measurement, product design, and policy approaches. Important open problems include multi-stakeholder processes for defining values and resolving trade-offs, better values-driven measurements, recommender controls that people use, non-behavioral algorithmic feedback, optimization for long-term outcomes, causal inference of recommender effects, academic-industry research collaborations, and interdisciplinary policy-making.Keywords
All Related Versions
This publication has 260 references indexed in Scilit:
- Media and Political PolarizationAnnual Review of Political Science, 2013
- The challenge of defining wellbeingInternational Journal of Wellbeing, 2012
- Human ComputationSynthesis Lectures on Artificial Intelligence and Machine Learning, 2011
- Unpacking the misery multiplier: How employability modifies the impacts of unemployment and job insecurity on life satisfaction and mental healthJournal of Health Economics, 2011
- Negative Intergroup Contact Makes Group Memberships Salient: Explaining Why Intergroup Conflict EnduresPersonality and Social Psychology Bulletin, 2010
- Construct Validity: Advances in Theory and MethodologyAnnual Review of Clinical Psychology, 2009
- The Warwick-Edinburgh Mental Well-being Scale (WEMWBS): development and UK validationHealth and Quality of Life Outcomes, 2007
- Symposium on Amartya Sen's philosophy: 2 Unstrapping the straitjacket of ‘preference’: a comment on Amartya Sen's contributions to philosophy and economicsEconomics and Philosophy, 2001
- Question Wording and Response Bias: Students' Perceptions of Ethical Issues in the Hospitality and Tourism IndustryJournal of Hospitality & Tourism Education, 1997
- Response bias, social desirability and dissimulationPersonality and Individual Differences, 1986