The DOI matches its Crossref record; 16 of the 16 references it cites were found in a registry or an index.
Degenerate Feedback Loops in Recommender Systems
Open accessAbstract
Machine learning is used extensively in recommender systems deployed in products. The decisions made by these systems can influence user beliefs and preferences which in turn affect the feedback the learning system receives - thus creating a feedback loop. This phenomenon can give rise to the so-called "echo chambers" or "filter bubbles" that have user and societal implications. In this paper, we provide a novel theoretical analysis that examines both the role of user dynamics and the behavior of recommender systems, disentangling the echo chamber from the filter bubble effect. In addition, we offer practical solutions to slow down system degeneracy. Our study contributes toward understanding and developing solutions to commonly cited issues in the complex temporal scenario, an area that is still largely unexplored.
Overview
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
Verification
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?
The cited source says what the claim attributes to it.
In the citing paper
“Usually, a biased system generates the biased output, and the uncontrolled biases can lead to the uneven distribution of opportunities and resources [58, 78], exacerbating the “ 𝐸𝑐ℎ𝑜 𝐶ℎ𝑎𝑚𝑏𝑒𝑟 ” or “ 𝐹𝑖𝑙𝑡𝑒𝑟 𝐵𝑢𝑏𝑏𝑙𝑒𝑠 ” effects [86, 87].”
From A Deep Dive into Fairness, Bias, Threats, and Privacy in Recommender Systems: Insights and Future Research (2024) · cites this paper as [87]
In the citing paper
“It is important to note that user engagement is a signal of value to both users and platforms deploying algorithms, connecting them in complex feedback loops 144,145 :”
From Machine culture (2023) · cites this paper as [145]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Finite-time Analysis of the Multiarmed Bandit Problem
Auer, P., Cesa-Bianchi, N., & Fischer, P. (2002) · Machine Learning · doi:10.1023/a:1013689704352 · Cited by 6,033
Deep Neural Networks for YouTube Recommendations
Covington, P., Adams, J., & Sargin, E. (2016) · Proceedings of the 10th ACM Conference on Recommender Systems · doi:10.1145/2959100.2959190 · Cited by 3,539
Exposure to ideologically diverse news and opinion on Facebook
Bakshy, E., Messing, S., & Adamic, L. A. (2015) · Science · doi:10.1126/science.aaa1160 · Cited by 3,245
THOMPSON, W. R. (1933) · Biometrika · doi:10.1093/biomet/25.3-4.285 · Cited by 2,712
Filter Bubbles, Echo Chambers, and Online News Consumption
Flaxman, S., Goel, S., & Rao, J. M. (2016) · Public Opinion Quarterly · doi:10.1093/poq/nfw006 · Cited by 1,992
FILTER BUBBLE: Wie wir im Internet entmündigt werden
Pariser, E. (2012) · doi:10.3139/9783446431164 · Cited by 1,849
Recommender system application developments: A survey
Jie Lu, B., Wu, D., Mao, M., Wang, W., & Zhang, G. (2015) · Decision Support Systems · doi:10.1016/j.dss.2015.03.008 · Cited by 1,584
E-Commerce Recommendation Applications
Schafer, J. B., Konstan, J. A., & Riedl, J. (2001) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009804230409 · Cited by 1,534
Tweeting From Left to Right: Is Online Political Communication More Than an Echo Chamber?
Barberá, P., Jost, J. T., Nagler, J., Tucker, J. A., & Bonneau, R. (2015) · Psychological Science · doi:10.1177/0956797615594620 · Cited by 1,472
Lattimore, T., & Szepesvári, C. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108571401 · Cited by 1,196
Self-citation
Research works printed but not linked: 2
- E. Pariser . 2011. The Filter Bubble: What the Internet is Hiding from You . Penguin UK. E. Pariser. 2011. The Filter Bubble: What the Internet is Hiding from You .Penguin UK.
- C. R. Sunstein. 2009. Republich.com 2.0 .Princeton University Press. C. R. Sunstein. 2009. Republich.com 2.0 .Princeton University Press.
Cited by
Sorted by citations
Items 201–231 of 231
Kuran, E. C., & Kuran, U. (2026) · Social Science Computer Review · doi:10.1177/08944393261419796
Cursed by the Algorithm: Cue-Triggered Consumption and Platform RecommendationPreprint
Firullo, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6265139
Chen, Q., & Hegde, V. G. (2025) · IEEE International Conference on Cognitive Machine Intelligence (CogMI) · doi:10.1109/cogmi67134.2025.00041
From Engagement to Empowerment: A Capability-Theoretic Rethinking of Recommender Systems
Vineis, V., & Tolomei, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-21324-2_28
Deep Natural Language Processing for User Representation
de Gabriac, C. G. D. F. (2021) · theses.fr (ABES) · doi:10.70675/f1d99786zd4d3z4d46z9b86z5de95a2b3290
LACEREC: Controllable Sequential Recommendation with Weak-Signal Enhancement
Zhang, X., Zhang, T. A., Cui, Z., Yu, M., Liu, H., Yu, Y., & Yu, G. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463590
Benveniste, M., Yamshchikov, I. P., & Fletcher, A. (2026) · Computational Humanities Research · doi:10.1017/chr.2026.10033
Unfairness in Information Retrieval
Mishra, H., & Soundarajan, S. (2026) · SpringerBriefs in intelligent systems · doi:10.1007/978-3-032-24145-0_2
EchoShield: Understanding Structural Hole Spanners to Mitigate Echo Chambers
Rajashekar, M., Govind, P. C. S., Thirumalareddy, S. R., Sankar, N. S., Chakraborty, R., Bertini, F., & Bhattacharya, M. (2026) · ACM Web Science Conference (WebSci) · doi:10.1145/3795513.3807428
Studying Longitudinal Effects of Recommender Systems: A Multi-Method Approach
Holzleitner, M. (2026) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3774935.3803057
The Socio-Technicality of Digital Peacebuilding
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0003
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.002.0004
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0004
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0006
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0001
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.001.0001
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0008
Digitalization, Technology, and the Voids of Peacebuilding
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0002
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0007
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.002.0005
Hirblinger, A. T. (2026) · doi:10.1093/9780198986553.003.0005
Like It or Not — Recommender Systems Lack a Coherent Normative Foundation
Khosrowi, D., & Beck, L. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3806531
EchoShield: Understanding Structural Hole Spanners to Mitigate Echo Chambers
Reddy, T. S., Rajashekar, M., Govind, P. C. S., Sankar, N. S., Chakraborty, R., Bertini, F., & Bhattacharya, M. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-2014-4_30
Johnston, E., & Liu, X. (2026) · Computers in Human Behavior Reports · doi:10.1016/j.chbr.2026.101214
Voinea, D. V. (2026) · Social Sciences · doi:10.3390/socsci15080496
Competing for Attention: A Stochastic Analysis of Influencer Popularity Dynamics
Galante, F., Ravazzi, C., Vassio, L., Garetto, M., & Leonardi, E. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3715706
Ju, Y., Lee, J., & Park, S. (2026) · Electronics · doi:10.3390/electronics15173917
Privacy in the AI Age From Information Control to Dynamic Person-ModelsPreprint
Wang, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7452698
Algorithmic systems, human agency and the future of platform research
Hosseinmardi, H., Dutta, U., Rothschild, D. M., & Watts, D. J. (2026) · Nature Computational Science · doi:10.1038/s43588-026-01038-1
There’s Something About You: Epistemic Recommendation for Latent Interest Discovery
Nemirovsky, D., Khokher, P. N. S., Jois, A., Zagha, M., & Delgado, J. (2026) · Proceedings of the 20th ACM Conference on Recommender Systems · doi:10.1145/3773078.3831822
Roy, F., Ding, X., Choo, K. K. R., & Zhou, P. (2024) · arXiv · doi:10.48550/arxiv.2409.12651 · Cited by 7
Metadata
- Authors
- Jiang, R., Chiappa, S., Lattimore, T., György, A., & Kohli, P.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Venue
- Proceedings of the 2019 AAAI/ACM Conference on AI, Ethics, and Society
- Publisher
- ACM
- Published
- 2019-01-27
- Pages
- 383-390
- ISSN
- 3065-8365 (ISSN-L)
- OpenAlex
- W2917760808
- Cited by
- 232
- References
- 15
- Citations by year
- 2026: 37 · 2025: 23 · 2024: 46 · 2023: 34 · 2022: 34 · 2021: 30 · 2020: 20 · 2019: 8
- FWCI
- 18.17
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Proceedings of the AAAI/ACM Conference on AI Ethics and Society (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Decision Sciences › Management Science and Operations Research › Advanced Bandit Algorithms Research
- Keywords
- recommender systems, feedback loops, degeneracy, echo chambers, filter bubbles, user dynamics, temporal dynamics
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
