Preference Dynamics Under Personalized Recommendations
Open accessAbstract
The design of content recommendation systems underpins many online platforms: social media feeds, online news aggregators, and audio/video hosting websites all choose how best to organize an enormous amount of content for users to consume. Many projects (both practical and academic) have designed algorithms to match users to content they will enjoy under the assumption that user's preferences and opinions do not change with the content they see.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Consumers may adjust their preferences and behaviors in response to the alternatives and information provided by AI systems, a phenomenon already observed in interactions with recommender systems.
“In turn, consumers may adjust their preferences and behaviors in response to the alternatives and information provided by AI systems-a phenomenon already observed in interactions with recommender systems (Dean and Morgenstern 2022).”
From Machine marketing: rethinking the customer in the age of generative AI (2026) · cites this paper as Dean and Morgenstern 2022
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Degenerate Feedback Loops in Recommender Systems
Jiang, R., Chiappa, S., Lattimore, T., György, A., & Kohli, P. (2019) · Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3306618.3314288 · Cited by 232 · see citing works
Flagged first, then by citations
Research works printed but not linked: 33
- M Mehdi Afsar, Trafford Crump, and Behrouz Far. Reinforcement learning based recommender systems: A survey. arXiv preprint arXiv:2101.06286, 2021. · arXiv
- B Douglas Bernheim, Luca Braghieri, Alejandro Martínez-Marquina, and David Zuckerman. A theory of chosen preferences. American Economic Review, 111(2):720-54, 2021.
- Gavin Brown, Shlomi Hod, and Iden Kalemaj. Performative prediction in a stateful world. In International Conference on Artificial Intelligence and Statistics, pages 6045-6061. PMLR, 2022.
- Micah Carroll, Dylan Hadfield-Menell, Stuart Russell, and Anca Dragan. Estimating and penalizing preference shift in recommender systems. In Fifteenth ACM Conference on Recommender Systems, RecSys '21, page 661-667. Association for Computing Machinery, 2021. ISBN 9781450384582.
- Allison JB Chaney, Brandon M Stewart, and Barbara E Engelhardt. How algorithmic confounding in recommendation systems increases homogeneity and decreases utility. In ACM Conference on Recommender Systems (RecSys), pages 224-232, 2018.
- Minmin Chen, Alex Beutel, Paul Covington, Sagar Jain, Francois Belletti, and Ed H Chi. Top-k off-policy correction for a reinforce recommender system. In International Conference on Web Search and Data Mining (WSDM), pages 456-464, 2019.
- Maurizio Ferrari Dacrema, Simone Boglio, Paolo Cremonesi, and Dietmar Jannach. A troubling analysis of reproducibility and progress in recommender systems research. ACM Transactions on Information Systems (TOIS), 39(2):1-49, 2021.
- Pranav Dandekar, Ashish Goel, and David Lee. Biased assimilation, homophily, and the dynamics of polarization. In National Academy of Sciences, pages 5791-5796, 2013.
- Christopher De Sa, Christopher Re, and Kunle Olukotun. Global convergence of stochastic gradient descent for some non-convex matrix problems. In International conference on machine learning, pages 2332-2341. PMLR, 2015.
- Jean-Pierre Dedieu, Pierre Priouret, and Gregorio Malajovich. Newton's method on riemannian manifolds: covariant alpha theory. IMA Journal of Numerical Analysis, 23(3):395-419, 2003.
- Charles Evans and Atoosa Kasirzadeh. User tampering in reinforcement learning recommender systems. arXiv preprint arXiv:2109.04083, 2021. · arXiv
- Jan Hązła, Yan Jin, Elchanan Mossel, and Govind Ramnarayan. A geometric model of opinion polarization. arXiv preprint arXiv:1910.05274, 2019. · arXiv
- De Huang, Jonathan Niles-Weed, and Rachel Ward. Streaming k-pca: Efficient guarantees for oja's algorithm, beyond rank-one updates. In Conference on Learning Theory, pages 2463-2498.
- PMLR, 2021.
- Eugene Ie, Vihan Jain, Jing Wang, Sanmit Navrekar, Ritesh Agarwal, Rui Wu, Heng-Tze Cheng, Morgane Lustman, Vince Gatto, Paul Covington, et al. Reinforcement learning for slate-based recommender systems: A tractable decomposition and practical methodology. arXiv preprint arXiv:1905.12767, 2019. · arXiv
- Prateek Jain, Chi Jin, Sham M Kakade, Praneeth Netrapalli, and Aaron Sidford. Streaming pca: Matching matrix bernstein and near-optimal finite sample guarantees for oja's algorithm. In Conference on learning theory, pages 1147-1164. PMLR, 2016.
- Dimitris Kalimeris, Smriti Bhagat, Shankar Kalyanaraman, and Udi Weinsberg. Preference ampli- fication in recommender systems. In Conference on Knowledge Discovery & Data Mining, pages 805-815. ACM SIGKDD, 2021.
- Jon Kleinberg, Sendhil Mullainathan, and Manish Raghavan. The challenge of understand- ing what users want: Inconsistent preferences and engagement optimization. arXiv preprint arXiv:2202.11776, 2022. · arXiv
- Karl Krauth, Sarah Dean, Alex Zhao, Wenshuo Guo, Mihaela Curmei, Benjamin Recht, and Michael I Jordan. Do offline metrics predict online performance in recommender systems? arXiv preprint arXiv:2011.07931, 2020. · arXiv
- David Krueger, Tegan Maharaj, and Jan Leike. Hidden incentives for auto-induced distributional shift. arXiv preprint arXiv:2009.09153, 2020. · arXiv
- Liu Leqi, Fatma Kilinc Karzan, Zachary Lipton, and Alan Montgomery. Rebounding bandits for modeling satiation effects. Advances in Neural Information Processing Systems, 34, 2021.
- Eli Lucherini, Matthew Sun, Amy Winecoff, and Arvind Narayanan. T-recs: A simulation tool to study the societal impact of recommender systems. arXiv preprint arXiv:2107.08959, 2021. · arXiv
- Masoud Mansoury, Himan Abdollahpouri, Mykola Pechenizkiy, Bamshad Mobasher, and Robin Burke. Feedback loop and bias amplification in recommender systems. arXiv preprint arXiv:2007.13019, 2020. · arXiv
- Juan Perdomo, Tijana Zrnic, Celestine Mendler-Dünner, and Moritz Hardt. Performative prediction. In International Conference on Machine Learning (ICML), pages 7599-7609. PMLR, 2020.
- Mitas Ray, Dmitriy Drusvyatskiy, Maryam Fazel, and Lillian J Ratliff. Decision-dependent risk minimization in geometrically decaying dynamic environments. In Proceedings of the Association for the Advancement of Artificial Intelligence Conference on AI (AAAI), 2022.
- Steffen Rendle, Li Zhang, and Yehuda Koren. On the difficulty of evaluating baselines: A study on recommender systems. arXiv preprint arXiv:1905.01395, 2019. · arXiv
- Sven Schmit and Carlos Riquelme. Human interaction with recommendation systems. In Interna- tional Conference on Artificial Intelligence and Statistics (AIstats), pages 862-870, 2018.
- Jonathan Stray, Ivan Vendrov, Jeremy Nixon, Steven Adler, and Dylan Hadfield-Menell. What are you optimizing for? aligning recommender systems with human values. arXiv preprint arXiv:2107.10939, 2021. · arXiv
- Robert Henry Strotz. Myopia and inconsistency in dynamic utility maximization. The review of economic studies, 23(3):165-180, 1955.
- Jyun-Cheng Wang and Juo-Ping Lin. Are personalization systems really personal?-effects of con- formity in reducing information. In 36th Annual Hawaii International Conference on System Sciences, 2003. Proceedings of the, pages 10-pp. IEEE, 2003.
- Romain Warlop, Alessandro Lazaric, and Jérémie Mary. Fighting boredom in recommender systems with linear reinforcement learning. Advances in Neural Information Processing Systems, 31, 2018.
- Sirui Yao, Yoni Halpern, Nithum Thain, Xuezhi Wang, Kang Lee, Flavien Prost, Ed H Chi, Jilin Chen, and Alex Beutel. Measuring recommender system effects with simulated users. arXiv preprint arXiv:2101.04526, 2021. · arXiv
- Ruohan Zhan, Konstantina Christakopoulou, Ya Le, Jayden Ooi, Martin Mladenov, Alex Beutel, Craig Boutilier, Ed Chi, and Minmin Chen. Towards content provider aware recommender sys- tems: A simulation study on the interplay between user and provider utilities. In Proceedings of the Web Conference 2021, pages 3872-3883, 2021.
Cited by
Sorted by citations
AI Alignment with Changing and Influenceable Reward Functions
Carroll, M., Foote, D., Siththaranjan, A., Russell, S., & Dragan, A. (2024) · arXiv · doi:10.48550/arxiv.2405.17713 · Cited by 7 · see citing works
Machine marketing: rethinking the customer in the age of generative AI
Sarstedt, M., Adler, S. J., & Imschloss, M. (2026) · Journal of Marketing Analytics · doi:10.1057/s41270-026-00521-y · Cited by 3 · see citing works
Feedback Loops With Language Models Drive In-Context Reward Hacking
Pan, A., Jones, E., Jagadeesan, M., & Steinhardt, J. (2024) · arXiv · doi:10.48550/arxiv.2402.06627 · Cited by 3 · see citing works
“At a broader scale, the recommender platform’s algorithm may shape the behavior of content creators (Hodgson, 2021; Ben-Porat & Tennenholtz, 2018; Jagadeesan et al., 2022) or the preferences of users (Krueger et al., 2020; Carroll et al., 2022; Dean & Morgenstern, 2022).”
Background
- Authors
- Dean, S., & Morgenstern, J.
- Affiliations
- Cornell University (US)
- University of Washington (US)
- Venue
- Proceedings of the 23rd ACM Conference on Economics and Computation
- Publisher
- ACM
- Published
- 2022-07-12
- Pages
- 795-816
- OpenAlex
- W4285088850
- Cited by
- 21
- References
- 1
- Citations by year
- 2026: 5 · 2025: 7 · 2024: 6 · 2023: 3
- FWCI
- 3.58
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Economics and Computation (EC) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- nsf (2045402)
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Game Theory and Voting Systems
- Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- Keywords
- personalized recommendation, preference dynamics, content recommendation systems, user preferences, social media feeds
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
