Recommender systems, ground truth, and preference pollution

Abstract

Interactions between individuals and recommender systems can be viewed as a continuous feedback loop, consisting of pre-consumption and post-consumption phases. Pre-consumption, systems provide recommendations that are typically based on predictions of user preferences. They represent a valuable service for both providers and users as decision aids. After item consumption, the user provides post-consumption feedback (e.g., a preference rating) to the system, often used to improve the system's subsequent recommendations, completing the feedback loop. There is a growing understanding that this feedback loop can be a significant source of unintended consequences, introducing decisionmaking biases that can affect the quality of the "ground truth" preference data, which serves as the key input to modern recommender systems. This paper highlights two forms of bias that recommender systems inherently inflict on the "ground truth" preference data collected from users after item consumption: non-representativeness of such preference data and so-called "preference pollution," which denotes an unintended relationship between system recommendations and the user's post-consumption preference ratings. We provide an overview of these issues and their importance for the design and application of next-generation recommendation systems, including directions for future research.

Bias characterization, assessment, and mitigation in location-based recommender systems

“…It should be clear that polarization might be related to the concept of algorithmic bias, which has been widely studied in recommender systems (Jannach et al 2015;Bellogín et al 2017;Boratto et al 2019;Abdollahpouri et al 2017;Adamopoulos et al 2015;Adomavicius et al 2014;Ekstrand et al 2018;Guo and Dunson 2015;Jannach et al 2016). Algorithmic bias assumes that RSs reinforce a previously existing bias in the data.…”

Functional Framework for Multivariant E-Commerce User Interfaces

“…In the case of e-commerce, the most popular solutions are those that lead to the generation of product recommendations [46], including hybrid tools [47]. These approaches have been in practice for years and are justified by customer choices [48]. This does not mean, however, that there is no scope for further refinement of this approach, using various forms of optimization of the final recommendations [49].…”

10th Joint Workshop on Interfaces and Human Decision Making for Recommender Systems (IntRS’23)

“…The idea of merging the two workshops was motivated by the strong inter-relationship between the user interface and human decision-making topics. Since 2014, some of the main topics discussed in the workshop are about fairness and biases [3], user behaviors and personalization [46,60], explanation [13,36,71], data visualization and user interaction [67,69]. These research directions have been constantly discussed till today in the IntRS workshop, and they have been constantly extended and updated.…”