Authors: Allison June-Barlow Chaney , Brandon M. Stewart , Barbara E. Engelhardt - ACM Conference on Recommender Systems, RecSys 2018 cited by 318
Recommendation systems are ubiquitous and impact many domains; they have the potential to influence product consumption, individuals' perceptions of the world, and life-altering decisions. These systems are often evaluated or trained with data from users already exposed to algorithmic recommendations; this creates a pernicious feedback loop. Using simulations, we demonstrate how using data confounded in this way homogenizes user behavior without increasing utility.
✨ Checking sign-in… PDF Cited by View BibTeX Hide BibTeX View BibTeX Cite
Factorization meets the neighborhood: a… Factorization meets the neighborhood: a multifaceted collaborative filtering model From hits to niches? From hits to niches? Collaborative Filtering for Implicit Feedback… Collaborative Filtering for Implicit Feedback Datasets Collaborative prediction and ranking with… Collaborative prediction and ranking with non-random missing data Matrix Factorization Techniques for… Matrix Factorization Techniques for Recommender Systems Performance of recommender algorithms… Performance of recommender algorithms on top-n recommendation tasks Collaborative topic modeling for… Collaborative topic modeling for recommending scientific articles Recommender systems with social regularization Recommender systems with social regularization Evaluation of recommendations… Evaluation of recommendations: rating-prediction and ranking A Probabilistic Model for Using Social… A Probabilistic Model for Using Social Networks in Personalized Item Recommendation Modeling User Exposure in Recommendation Modeling User Exposure in Recommendation Diversity, Serendipity, Novelty, and Coverage… Diversity, Serendipity, Novelty, and Coverage: A Survey and Empirical Analysis of Beyond-Accuracy Objectives in Recommender Systems Modeling and counteracting exposure… Modeling and counteracting exposure bias in recommender systems. Correcting for Selection Bias in Learning-to-ran… Correcting for Selection Bias in Learning-to-rank Systems Evaluating Stochastic Rankings with Expected… Evaluating Stochastic Rankings with Expected Exposure Measuring Recommender System Effects with… Measuring Recommender System Effects with Simulated Users Causal Intervention for Leveraging Popularity… Causal Intervention for Leveraging Popularity Bias in Recommendation Recommender systems effect on the evolution… Recommender systems effect on the evolution of users' choices distribution Popularity Bias Is Not Always Evil… Popularity Bias Is Not Always Evil: Disentangling Benign and Harmful Bias for Recommendation Bias and Debias in Recommender System: A… Bias and Debias in Recommender System: A Survey and Future Directions Fair ranking: a critical review, challenges, and… Fair ranking: a critical review, challenges, and future directions CIRS: Bursting Filter Bubbles by… CIRS: Bursting Filter Bubbles by Counterfactual Interactive Recommender System DPR: An Algorithm Mitigate Bias… DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops Causal Inference for Recommendation… Causal Inference for Recommendation: Foundations, Methods, and Applications How Algorithmic Confounding in… How Algorithmic Confounding in Recommendation Systems Increases Homogeneity and Decreases Utility Earlier references Focus paper Citing papers Older Newer Click a node to pin it, click the empty canvas to go back to this paper, or hover to preview. Open a node’s page from its title.
