skip to main content


This content will become publicly available on March 19, 2024

Title: Toward A Two-Sided Fairness Framework in Search and Recommendation
As artificial intelligence (AI) assisted search and recommender systems have become ubiquitous in workplaces and everyday lives, understanding and accounting for fairness has gained increasing attention in the design and evaluation of such systems. While there is a growing body of computing research on measuring system fairness and biases associated with data and algorithms, the impact of human biases that go beyond traditional machine learning (ML) pipelines still remain understudied. In this Perspective Paper, we seek to develop a two-sided fairness framework that not only characterizes data and algorithmic biases, but also highlights the cognitive and perceptual biases that may exacerbate system biases and lead to unfair decisions. Within the framework, we also analyze the interactions between human and system biases in search and recommendation episodes. Built upon the two-sided framework, our research synthesizes intervention and intelligent nudging strategies applied in cognitive and algorithmic debiasing, and also proposes novel goals and measures for evaluating the performance of systems in addressing and proactively mitigating the risks associated with biases in data, algorithms, and bounded rationality. This paper uniquely integrates the insights regarding human biases and system biases into a cohesive framework and extends the concept of fairness from human-centered perspective. The extended fairness framework better reflects the challenges and opportunities in users’ interactions with search and recommender systems of varying modalities. Adopting the two-sided approach in information system design has the potential to enhancing both the effectiveness in online debiasing and the usefulness to boundedly rational users engaging in information-intensive decision-making.  more » « less
Award ID(s):
2106152
NSF-PAR ID:
10422199
Author(s) / Creator(s):
Date Published:
Journal Name:
CHIIR '23: Proceedings of the 2023 Conference on Human Information Interaction and Retrieval
Page Range / eLocation ID:
236 to 246
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. null (Ed.)
    Graph mining is an essential component of recommender systems and search engines. Outputs of graph mining models typically provide a ranked list sorted by each item's relevance or utility. However, recent research has identified issues of algorithmic bias in such models, and new graph mining algorithms have been proposed to correct for bias. As such, algorithm developers need tools that can help them uncover potential biases in their models while also exploring the impacts of correcting for biases when employing fairness-aware algorithms. In this paper, we present FairRankVis, a visual analytics framework designed to enable the exploration of multi-class bias in graph mining algorithms. We support both group and individual fairness levels of comparison. Our framework is designed to enable model developers to compare multi-class fairness between algorithms (for example, comparing PageRank with a debiased PageRank algorithm) to assess the impacts of algorithmic debiasing with respect to group and individual fairness. We demonstrate our framework through two usage scenarios inspecting algorithmic fairness. 
    more » « less
  2. A large number of two-sided markets are now mediated by search and recommender systems, ranging from online retail and streaming entertainment to employment and romantic-partner matching. I will discuss in this talk how the design decisions that go into these search and recommender systems carry substantial power in shaping markets and allocating opportunity to the participants. This does not only raise legal and fairness questions, but also questions about how these systems shape incentives and the long-term effectiveness of the market. At the core of these questions lies the problem of where to rank each item, and how this affects both sides of the market. While it is well understood how to maximize the utility to the users, this talk focuses on how rankings affect the items that are being ranked. From the items perspective, the ranking system is an arbiter of exposure and thus economic opportunity. I will discuss how machine learning algorithms that follow the conventional Probability Ranking Principle [1] can lead to undesirable and unfair exposure allocation for both exogenous and endogenous reasons. Exogenous reasons often manifest themselves as biases in the training data, which then get reflected in the learned ranking policy. But even when trained with unbiased data, reasons endogenous to the system can lead to unfair or undesirable allocation of opportunity. To overcome these challenges, I will present new machine learning algorithms [2,3,4] that directly address both endogenous and exogenous factors, allowing the designer to tailor the ranking policy to be appropriate for the specific two-sided market. 
    more » « less
  3. null (Ed.)
    Purpose The purpose of this paper is to offer a critical analysis of talent acquisition software and its potential for fostering equity in the hiring process for underrepresented IT professionals. The under-representation of women, African-American and Latinx professionals in the IT workforce is a longstanding issue that contributes to and is impacted by algorithmic bias. Design/methodology/approach Sources of algorithmic bias in talent acquisition software are presented. Feminist design thinking is presented as a theoretical lens for mitigating algorithmic bias. Findings Data are just one tool for recruiters to use; human expertise is still necessary. Even well-intentioned algorithms are not neutral and should be audited for morally and legally unacceptable decisions. Feminist design thinking provides a theoretical framework for considering equity in the hiring decisions made by talent acquisition systems and their users. Social implications This research implies that algorithms may serve to codify deep-seated biases, making IT work environments just as homogeneous as they are currently. If bias exists in talent acquisition software, the potential for propagating inequity and harm is far more significant and widespread due to the homogeneity of the specialists creating artificial intelligence (AI) systems. Originality/value This work uses equity as a central concept for considering algorithmic bias in talent acquisition. Feminist design thinking provides a framework for fostering a richer understanding of what fairness means and evaluating how AI software might impact marginalized populations. 
    more » « less
  4. With the rise of AI, algorithms have become better at learning underlying patterns from the training data including ingrained social biases based on gender, race, etc. Deployment of such algorithms to domains such as hiring, healthcare, law enforcement, etc. has raised serious concerns about fairness, accountability, trust and interpretability in machine learning algorithms. To alleviate this problem, we propose D-BIAS, a visual interactive tool that embodies human-in-the-loop AI approach for auditing and mitigating social biases from tabular datasets. It uses a graphical causal model to represent causal relationships among different features in the dataset and as a medium to inject domain knowledge. A user can detect the presence of bias against a group, say females, or a subgroup, say black females, by identifying unfair causal relationships in the causal network and using an array of fairness metrics. Thereafter, the user can mitigate bias by refining the causal model and acting on the unfair causal edges. For each interaction, say weakening/deleting a biased causal edge, the system uses a novel method to simulate a new (debiased) dataset based on the current causal model while ensuring a minimal change from the original dataset. Users can visually assess the impact of their interactions on different fairness metrics, utility metrics, data distortion, and the underlying data distribution. Once satisfied, they can download the debiased dataset and use it for any downstream application for fairer predictions. We evaluate D-BIAS by conducting experiments on 3 datasets and also a formal user study. We found that D-BIAS helps reduce bias significantly compared to the baseline debiasing approach across different fairness metrics while incurring little data distortion and a small loss in utility. Moreover, our human-in-the-loop based approach significantly outperforms an automated approach on trust, interpretability and accountability. 
    more » « less
  5. In the past few years, there has been much work on incorporating fairness requirements into the design of algorithmic rankers, with contributions from the data management, algorithms, information retrieval, and recommender systems communities. In this tutorial, we give a systematic overview of this work, offering a broad perspective that connects formalizations and algorithmic approaches across subfields. During the first part of the tutorial, we present a classification framework for fairness-enhancing interventions, along which we will then relate the technical methods. This framework allows us to unify the presentation of mitigation objectives and of algorithmic techniques to help meet those objectives or identify trade-offs. Next, we discuss fairness in score-based ranking and in supervised learning-to-rank. We conclude with recommendations for practitioners, to help them select a fair ranking method based on the requirements of their specific application domain. 
    more » « less