Degenerate Feedback Loops in Recommender Systems

Jiang, Ray; Chiappa, Silvia; Lattimore, Tor; György, András; Kohli, Pushmeet

doi:10.1145/3306618.3314288

Cited by 135 publications

(114 citation statements)

References 18 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…Despite the reasonableness of prior works, severe limitations do exist, making the claims only plausible. One major aspect is that most of the existing works draw conclusions by means of simulation, or relying on some self-defined networks and measurements with simplified dynamics [6,9,15,20,26,31]. Building upon the subjective assumptions, whether the modeling and analysis have the capability to reflect the truth seems to be dubious [37].…”

Section: Related Workmentioning

confidence: 99%

Understanding Echo Chambers in E-commerce Recommender Systems

Zhao

Zhou

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Personalized recommendation benefits users in accessing contents of interests effectively. Current research on recommender systems mostly focuses on matching users with proper items based on user interests. However, significant efforts are missing to understand how the recommendations influence user preferences and behaviors, e.g., if and how recommendations result in echo chambers. Extensive efforts have been made in examining the phenomenon in online media and social network systems. Meanwhile, there are growing concerns that recommender systems might lead to the self-reinforcing of user's interests due to narrowed exposure of items, which may be the potential cause of echo chamber. In this paper, we aim to analyze the echo chamber phenomenon in Alibaba Taobao-one of the largest e-commerce platforms in the world. Echo chamber means the effect of user interests being reinforced through repeated exposure to similar contents. Based on the definition, we examine the presence of echo chamber in two steps. First, we explore whether user interests have been reinforced. Second, we check whether the reinforcement results from the exposure of similar contents. Our evaluations are enhanced with robust metrics, including cluster validity and statistical significance. Experiments are performed on extensive collections of real-world data consisting of user clicks, purchases, and browse logs from Alibaba Taobao. Evidence suggests the tendency of echo chamber in user click behaviors, while it is relatively mitigated in user purchase behaviors. Insights from the results guide the refinement of recommendation algorithms in real-world e-commerce systems. CCS CONCEPTS • Information systems → Recommender systems; Web log analysis; Test collections. * Co-first authors with equal contributions. † This work was done when Yingqiang Ge worked as an intern in Alibaba.

show abstract

Section: Related Workmentioning

confidence: 99%

Understanding Echo Chambers in E-commerce Recommender Systems

Zhao

Zhou

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…AI can play multiple roles in a system, from being an element, such as teaching robots used in primary schools (Breazeal 2019). It could also play a role as an organizing force, as many people experience when using social media such as Google Maps and Facebook, or in self-reinforcing feedback loops facilitating the achievement of something, such as Amazon or YouTube's recommender systems designed to change behavior patterns (Jiang et al 2019).…”

Section: Systems-based Approachmentioning

confidence: 99%

Artificial Intelligence and Community Well-being: A Proposal for an Emerging Area of Research

Musikanski¹,

Rakova

Bradbury³

et al. 2020

Int. Journal of Com. WB

View full text Add to dashboard Cite

We are calling for a new area of research on the nexus of community well-being and artificial intelligence (AI). Three components of this research we propose are (1) the development and use of well-being metrics to measure the impacts of AI; (2) the use of community-based approaches in the development of AI; and (3) development of AI interventions to safeguard or improve community well-being. After providing definitions of community, well-being, and community well-being, we suggest a definition of AI for use by community well-being researchers, with brief explanations of types and uses of AI within this context. A brief summary of threats and opportunities facing community well-being for which AI could potentially present solutions or exacerbate problems is provided. The three components we propose are then discussed, followed by our call for cross-sector, interdisciplinary, transdisciplinary and systems-based approaches for the formation of this proposed area of research.

show abstract

“…Some methods use post learning techniques which consist of different ranking and arXiv:2001.04832v1 [cs.IR] 1 Jan 2020 selection strategies after performing the predictions. In this family, we find a big interest in Multi-Armed Bandit techniques [12] since they have proven to be efficient in the exploitation vs exploration problems [13]. MAB are good with exploration problems, they are often used in Recommender systems in order to solve the exposure bias problem.…”

Section: Related Workmentioning

confidence: 99%

“…MAB are good with exploration problems, they are often used in Recommender systems in order to solve the exposure bias problem. For instance, a group of DeepMind researchers [12] have recently used MAB to study the effect of the feedback loop in recommender systems. They showed that the feedback loop can decrease the quality of the recommendations and they also showed that random exploration using Multi-Armed Bandit techniques can enhance and boost the quality of the predictions.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Modeling and counteracting exposure bias in recommender systems.

Khenissi

Nasraoui

View full text Add to dashboard Cite

What we discover and see online, and consequently our opinions and decisions, are becoming increasingly affected by automated machine learned predictions. Similarly, the predictive accuracy of learning machines heavily depends on the feedback data that we provide them. This mutual influence can lead to closed-loop interactions that may cause unknown biases which can be exacerbated after several iterations of machine learning predictions and user feedback. Machine-caused biases risk leading to undesirable social effects ranging from polarization to unfairness and filter bubbles.In this paper, we study the bias inherent in widely used recommendation strategies such as matrix factorization. Then we model the exposure that is borne from the interaction between the user and the recommender system and propose new debiasing strategies for these systems.Finally, we try to mitigate the recommendation system bias by engineering solutions for several state of the art recommender system models.Our results show that recommender systems are biased and depend on the prior exposure of the user. We also show that the studied bias iteratively decreases diversity in the output recommendations. Our debiasing method demonstrates the need for alternative recommendation strategies that take into account the exposure process in order to reduce bias.Our research findings show the importance of understanding the nature of and dealing with bias in machine learning models such as recommender systems that interact directly with humans, and are thus causing an increasing influence on human discovery and decision making.

show abstract

Degenerate Feedback Loops in Recommender Systems

Cited by 135 publications

References 18 publications

Understanding Echo Chambers in E-commerce Recommender Systems

Understanding Echo Chambers in E-commerce Recommender Systems

Artificial Intelligence and Community Well-being: A Proposal for an Emerging Area of Research

Modeling and counteracting exposure bias in recommender systems.

Contact Info

Product

Resources

About