Feedback Loop and Bias Amplification in Recommender Systems
Open accessThe DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Recommendation algorithms are known to suffer from popularity bias; a few popular items are recommended frequently while the majority of other items are ignored. These recommendations are then consumed by the users, their reaction will be logged and added to the system: what is generally known as a feedback loop. In this paper, we propose a method for simulating the users interaction with the recommenders in an offline setting and study the impact of feedback loop on the popularity bias amplification of several recommendation algorithms. We then show how this bias amplification leads to several other problems such as declining the aggregate diversity, shifting the representation of users' taste over time and also homogenization of the users. In particular, we show that the impact of feedback loop is generally stronger for the users who belong to the minority group.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
GroupLens: an open architecture for collaborative filtering of netnews
Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1994) · Proceedings of the 1994 ACM conference on Computer supported cooperative work - CSCW '94 · doi:10.1145/192844.192905 · Cited by 5,058
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 · cited 1×
“recommender systems has recently received more attention from researchers [4, 5, 9, 14–16].”
Background
Cited by
Bias and Debias in Recommender System: A Survey and Future Directions
Chen, J., Dong, H., Wang, X., Feng, F., Wang, M., & He, X. (2023) · ACM Transactions on Information Systems · doi:10.1145/3564284 · Cited by 741
“Many researchers also study the impact of feedback loop on the popularity bias [57], [58], [59].”
BackgroundCausal Intervention for Leveraging Popularity Bias in Recommendation
Zhang, Y., Feng, F., He, X., Wei, T., Song, C., Ling, G., & Zhang, Y. (2021) · Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3404835.3462875 · Cited by 443
How human–AI feedback loops alter human perceptual, emotional and social judgements
Glickman, M., & Sharot, T. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-02077-2 · Cited by 289
Giovanola, B., & Tiribelli, S. (2023) · AI & SOCIETY · doi:10.1007/s00146-022-01455-6 · Cited by 193
The Connection Between Popularity Bias, Calibration, and Fairness in Recommendation
Abdollahpouri, H., Mansoury, M., Burke, R., & Mobasher, B. (2020) · Fourteenth ACM Conference on Recommender Systems · doi:10.1145/3383313.3418487 · Cited by 183
Self-citationAI Fairness in Data Management and Analytics: A Review on Challenges, Methodologies and Applications
Chen, P., Wu, L., & Wang, L. (2023) · Applied Sciences · doi:10.3390/app131810258 · Cited by 155
Popularity Bias is not Always Evil: Disentangling Benign and Harmful Bias for Recommendation
Zhao, Z., Chen, J., Zhou, S., He, X., Cao, X., Zhang, F., & Wu, W. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2022.3218994 · Cited by 117
“but also amplifies bias, making the popular items dominate the top recommendations [13], [19], [20], [21], [22], [23].”
BackgroundPedreschi, D., Pappalardo, L., Ferragina, E., Baeza-Yates, R., Barabási, A.-L., Dignum, F., Dignum, V., Eliassi-Rad, T., Giannotti, F., Kertész, J., et al. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2024.104244 · Cited by 102
“There is a handful of studies that move beyond the static investigation of the influence of recommenders on users’ behaviour, analysing feedback loop mechanisms theoretically and/or empirically [11–13, 94, 95].”
Survey on Machine Learning Biases and Mitigation Techniques
Siddique, S., Haque, M. A., George, R., Gupta, K. D., Gupta, D., & Faruk, M. J. H. (2023) · Digital · doi:10.3390/digital4010001 · Cited by 78
Towards Understanding the Interplay of Generative Artificial Intelligence and the Internet
Martínez, G., Watson, L., Reviriego, P., Hernández, J. A., Juarez, M., & Sarkar, R. (2023) · arXiv · doi:10.48550/arxiv.2306.06130 · Cited by 36
Embedding Societal Values into Social Media Algorithms
Bernstein, M., Christin, A., Hancock, J., Hashimoto, T., Jia, C., Lam, M., Meister, N., Persily, N., Piccardi, T., Saveski, M., et al. (2023) · Journal of Online Trust and Safety · doi:10.54501/jots.v2i1.148 · Cited by 31
User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms
Wang, N., & Chen, L. (2021) · Fifteenth ACM Conference on Recommender Systems · doi:10.1145/3460231.3474244 · Cited by 22
“For instance, [31] studied how algorithms intensify the existing bias in historical data by applying algorithms to generate recommendations for multiple iterations and then observing the change of average popularity of recommendation lists over time.”
BackgroundHuang, J., Oosterhuis, H., Mansoury, M., van Hoof, H., & de Rijke, M. (2024) · Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3626772.3657749 · Cited by 17
Self-citationAgentic Feedback Loop Modeling Improves Recommendation and User Simulation
Cai, S., Zhang, J., Bao, K., Gao, C., Wang, Q., Feng, F., & He, X. (2024) · arXiv · doi:10.48550/arxiv.2410.20027 · Cited by 14
Sikimić, V., & Radovanović, S. (2022) · European Journal for Philosophy of Science · doi:10.1007/s13194-022-00478-6 · Cited by 14
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
“The resulting feedback loops can increase homogeneity (Chaney et al., 2018) and bias (Mansoury et al., 2020).”
BackgroundPerformative Reinforcement Learning
Mandal, D., Triantafyllou, S., & Radanovic, G. (2022) · arXiv · doi:10.48550/arxiv.2207.00046
Metadata
- Authors
- Mansoury, M., Abdollahpouri, H., Pechenizkiy, M., Mobasher, B., & Burke, R.
- Venue
- Proceedings of the 29th ACM International Conference on Information & Knowledge Management
- Publisher
- ACM
- Published
- 2020-10-19
- Pages
- 2145-2148
- ISSN
- 2155-0751 (ISSN-L)
- OpenAlex
- W3044938582
- Cited by
- 228
- References
- 2
- FWCI
- 20.64
- Type
- conference paper
- Language
- en
- Open access
- green
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
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.