Appropriate Fairness Perceptions? On the Effectiveness of Explanations in Enabling People to Assess the Fairness of Automated Decision Systems
Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院）
Jakob Schoeffer, Niklas Kuehl
备注：
Companion Publication of the 2021 Conference on Computer Supported Cooperative Work and Social Computing (CSCW '21 Companion), October 23--27, 2021, Virtual Event, USA
It is often argued that one goal of explaining automated decision systems (ADS) is to facilitate positive perceptions (e.g., fairness or trustworthiness) of users towards such systems. This viewpoint, however, makes the implicit assumption that a given ADS is fair and trustworthy, to begin with. If the ADS issues unfair outcomes, then one might expect that explanations regarding the system's workings will reveal its shortcomings and, hence, lead to a decrease in fairness perceptions. Consequently, we suggest that it is more meaningful to evaluate explanations against their effectiveness in enabling people to appropriately assess the quality (e.g., fairness) of an associated ADS. We argue that for an effective explanation, perceptions of fairness should increase if and only if the underlying ADS is fair. In this in-progress work, we introduce the desideratum of appropriate fairness perceptions, propose a novel study design for evaluating it, and outline next steps towards a comprehensive experiment.
As Artificial Intelligence (AI) technology gets more intertwined with every system, people are using AI to make decisions on their everyday activities. In simple contexts, such as Netflix recommendations, or in more complex context like in judicial scenarios, AI is part of people's decisions. People make decisions and usually, they need to explain their decision to others or in some matter. It is particularly critical in contexts where human expertise is central to decision-making. In order to explain their decisions with AI support, people need to understand how AI is part of that decision. W…
Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）；University of Texas at Austin（德克萨斯大学奥斯汀分校）
It is known that recommendations of AI-based systems can be incorrect or unfair. Hence, it is often proposed that a human be the final decision-maker. Prior work has argued that explanations are an essential pathway to help human decision-makers enhance decision quality and mitigate bias, i.e., facilitate human-AI complementarity. For these benefits to materialize, explanations should enable humans to appropriately rely on AI recommendations and override the algorithmic recommendation when necessary to increase distributive fairness of decisions. The literature, however, does not provide concl…
Automated decision systems (ADS) have become ubiquitous in many high-stakes domains. Those systems typically involve sophisticated yet opaque artificial intelligence (AI) techniques that seldom allow for full comprehension of their inner workings, particularly for affected individuals. As a result, ADS are prone to deficient oversight and calibration, which can lead to undesirable (e.g., unfair) outcomes. In this work, we conduct an online study with 200 participants to examine people's perceptions of fairness and trustworthiness towards ADS in comparison to a scenario where a human instead of…
Karlsruhe Institute of Technology (KIT)（卡尔斯鲁厄理工学院（KIT））
Automated decision systems are increasingly used for consequential decision making -- for a variety of reasons. These systems often rely on sophisticated yet opaque models, which do not (or hardly) allow for understanding how or why a given decision was arrived at. This is not only problematic from a legal perspective, but non-transparent systems are also prone to yield undesirable (e.g., unfair) outcomes because their sanity is difficult to assess and calibrate in the first place. In this work, we conduct a study to evaluate different attempts of explaining such systems with respect to their …
This article examines the concept of 'AI fairness' for people with disabilities from the perspective of data protection and equality law. This examination demonstrates that there is a need for a distinctive approach to AI fairness that is fundamentally different to that used for other protected characteristics, due to the different ways in which discrimination and data protection law applies in respect of Disability. We articulate this new agenda for AI fairness for people with disabilities, explaining how combining data protection and equality law creates new opportunities for disabled people…
Heinrich Heine University Düsseldorf（海因里希·海涅杜塞尔多夫大学）
Algorithmic decision-making (ADM) increasingly shapes people's daily lives. Given that such autonomous systems can cause severe harm to individuals and social groups, fairness concerns have arisen. A human-centric approach demanded by scholars and policymakers requires taking people's fairness perceptions into account when designing and implementing ADM. We provide a comprehensive, systematic literature review synthesizing the existing empirical insights on perceptions of algorithmic fairness from 39 empirical studies spanning multiple domains and scientific disciplines. Through thorough codin…
Automated decision systems (ADS) are increasingly used for consequential decision-making. These systems often rely on sophisticated yet opaque machine learning models, which do not allow for understanding how a given decision was arrived at. In this work, we conduct a human subject study to assess people's perceptions of informational fairness (i.e., whether people think they are given adequate information on and explanation of the process and its outcomes) and trustworthiness of an underlying ADS when provided with varying types of information about the system. More specifically, we instantia…
We discuss issues of Artificial Intelligence (AI) fairness for people with disabilities, with examples drawn from our research on human-computer interaction (HCI) for AI-based systems for people who are Deaf or Hard of Hearing (DHH). In particular, we discuss the need for inclusion of data from people with disabilities in training sets, the lack of interpretability of AI systems, ethical responsibilities of access technology researchers and companies, the need for appropriate evaluation metrics for AI-based access technologies (to determine if they are ready to be deployed and if they can be t…
Microsoft Research（微软研究院）；Carnegie Mellon University（卡内基梅隆大学）
AI technologies have the potential to dramatically impact the lives of people with disabilities (PWD). Indeed, improving the lives of PWD is a motivator for many state-of-the-art AI systems, such as automated speech recognition tools that can caption videos for people who are deaf and hard of hearing, or language prediction algorithms that can augment communication for people with speech or cognitive disabilities. However, widely deployed AI systems may not work properly for PWD, or worse, may actively discriminate against them. These considerations regarding fairness in AI for PWD have thus f…
Algorithmic processes are increasingly employed to perform managerial decision making, especially after the tremendous success in Artificial Intelligence (AI). This paradigm shift is occurring because these sophisticated AI techniques are guaranteeing the optimality of performance metrics. However, this adoption is currently under scrutiny due to various concerns such as fairness, and how does the fairness of an AI algorithm affects user's trust is much legitimate to pursue. In this regard, we aim to understand the relationship between induced algorithmic fairness and its perception in humans.…
Ensuring fairness of machine learning systems is a human-in-the-loop process. It relies on developers, users, and the general public to identify fairness problems and make improvements. To facilitate the process we need effective, unbiased, and user-friendly explanations that people can confidently rely on. Towards that end, we conducted an empirical study with four types of programmatically generated explanations to understand how they impact people's fairness judgments of ML systems. With an experiment involving more than 160 Mechanical Turk workers, we show that: 1) Certain explanations are…
There is increasing interest in Artificial Intelligence and its application to medicine. Perceptions are less well-known, notably amongst children and young people. 21 members of a Young Persons Advisory Group for research, recommend creating an enabling environment with children and young people, through educational workshops with practical examples that use Artificial Intelligence to help, but not replace humans, address issues, build trust, and effectively communicate about potential opportunities.
Previous research has shown that the fairness and the legitimacy of a moral decision-maker are important for people's acceptance of and compliance with the decision-maker. As technology rapidly advances, there have been increasing hopes and concerns about building artificially intelligent entities that are designed to intervene against norm violations. However, it is unclear how people would perceive artificial moral regulators that impose punishment on human wrongdoers. Grounded in theories of psychology and law, we predict that the perceived fairness of punishment imposed by a robot would in…
Makeup and cosmetics offer the potential for self-expression and the reshaping of social roles for visually impaired people. However, there exist barriers to conducting a beauty regime because of the reliance on visual information and color variances in makeup. We present a content analysis of 145 YouTube videos to demonstrate visually impaired individuals' unique practices before, during, and after doing makeup. Based on the makeup practices, we then conducted semi-structured interviews with 12 visually impaired people to discuss their perceptions of and challenges with the makeup process in …
Advances in tactile-audio feedback technology have created new possibilities for deaf people to feel music. However, little is known about deaf individuals' perception of musical emotions through vibrotactile feedback. In this paper, we present the findings from a mixed-methods study with 16 profoundly deaf participants. The study protocol was designed to explore how users of a backpack-style vibrotactile display perceive intended emotions in twenty music excerpts. Quantitative analysis demonstrated that participants correctly identified happy and angry excerpts and rated them as more arousing…
Smart home devices have found their way through people's homes as well as hearts. One such smart device is Amazon Alexa. Amazon Alexa is a voice-controlled application that is rapidly gaining popularity. Alexa was primarily used for checking weather forecasts, playing music, and controlling other devices. This paper tries to explore the extent to which people are aware of the privacy policies pertaining to the Amazon Alexa devices. We have evaluated behavioral change towards their interactions with the device post being aware of the adverse implications. Resulting knowledge will give researche…
Consumer speech recognition systems do not work as well for many people with speech diferences, such as stuttering, relative to the rest of the general population. However, what is not clear is the degree to which these systems do not work, how they can be improved, or how much people want to use them. In this paper, we frst address these questions using results from a 61-person survey from people who stutter and fnd participants want to use speech recognition but are frequently cut of, misunderstood, or speech predictions do not represent intent. In a second study, where 91 people who stutter…
Previous research found that robots should best be designed to fit their given task, whilst others identified gender effects in people's evaluations of robots. This study combines this knowledge to investigate stereotyping effects of robot genderedness and assigned tasks in an online experiment (n = 89) manipulating robot gender (male vs. female) and task type (analytical vs. social) in a between subject's design in terms of trust, social perception, and humanness. People deem robots more competent and have higher trust in their capacity when they perform analytical tasks compared to social ta…
Camera-based technology can be privacy-invasive, especially for bystanders who can be captured by the cameras but do not have direct control or access to the devices. The privacy threats become even more significant to bystanders with visual impairments (BVI) since they cannot visually discover the use of cameras nearby and effectively avoid being captured. While some prior research has studied visually impaired people's privacy concerns as direct users of camera-based assistive technologies, no research has explored their unique privacy perceptions and needs as bystanders. We conducted an in-…
While many people use social network sites to connect with friends and family, some feel that their use is problematic, seriously affecting their sleep, work, or life. Pairing a survey of 20,000 Facebook users measuring perceptions of problematic use with behavioral and demographic data, we examined Facebook activities associated with problematic use as well as the kinds of people most likely to experience it. People who feel their use is problematic are more likely to be younger, male, and going through a major life event such as a breakup. They spend more time on the platform, particularly a…
Algorithmic decision-making systems are increasingly used throughout the public and private sectors to make important decisions or assist humans in making these decisions with real social consequences. While there has been substantial research in recent years to build fair decision-making algorithms, there has been less research seeking to understand the factors that affect people's perceptions of fairness in these systems, which we argue is also important for their broader acceptance. In this research, we conduct an online experiment to better understand perceptions of fairness, focusing on t…
Artificial intelligence (AI) is everywhere, with many children having increased exposure to AI technologies in daily life. We aimed to understand middle school girls' (a group often excluded group in tech) perceptions and knowledge gaps about AI. We created and explored the feasibility of a lightweight (less than 3 hours) educational workshop in which learners considered challenges in their lives and communities and critically considered how existing and future AI could have an impact. After the workshop, learners had nuanced perceptions of AI, understanding AI can both help and harm. We discu…
The 'intuitive' trust people feel when encountering robots in public spaces is a key determinant of their willingness to cooperate with these robots. We conducted four experiments to study this topic in the context of peacekeeping robots. Participants viewed scenarios, presented as static images or animations, involving a robot or a human guard performing an access-control task. The guards interacted more or less politely with younger and older male and female people. Our results show strong effects of the guard's politeness. Age and sex of the people interacting with the guard had no signific…
We propose a research to investigate Saudi peoples' perception of humanoid domestic robots and attitude towards the possibility of having one in their house. Through a series of questionnaires, semi-structured interviews, focus groups, and participatory design sessions, this research will explore Saudi peoples' level of acceptance towards domestic robots, the tasks and responsibilities they would feel comfortable assigning to these robots, their preferred appearance of domestic robots, and the cultural stereotypes they feel a domestic robot must mimic.
KAIST（韩国科学技术院）；IBS（韩国基础科学研究院）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Max Planck Institute for Research on Collective Goods（马克斯·普朗克集体利益研究所）
How to attribute responsibility for autonomous artificial intelligence (AI) systems' actions has been widely debated across the humanities and social science disciplines. This work presents two experiments ($N$=200 each) that measure people's perceptions of eight different notions of moral responsibility concerning AI and human agents in the context of bail decision-making. Using real-life adapted vignettes, our experiments show that AI agents are held causally responsible and blamed similarly to human agents for an identical task. However, there was a meaningful difference in how people perce…
Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper robot to build an interaction model that stores the interpretations of perceptions and conversations in combination with provenance on its sources. The robot learns directly from what people tell it, possibly in relation to its perception. We demonstra…
Bangladesh, a developing country with a large and dense population, has recently seen significant economic as well as technological developments. The growth of technology has resulted in a dramatic increase in the number of smartphone users in Bangladesh, and as such, mobile apps have become an increasingly important part of peoples' life, even encompassing healthcare services. However, the apps used in healthcare (telemedicine to be specific) in Bangladesh are yet to be studied from the perspective of their features as per the voices of the users as well as service providers. Therefore, in th…
Beihang University（北京航空航天大学）；CloudMinds Technologies Inc.（达闼科技有限公司）；China Academy of Telecommunication Technology（中国电信技术研究院）
This paper presents a wearable assistive device with the shape of a pair of eyeglasses that allows visually impaired people to navigate safely and quickly in unfamiliar environment, as well as perceive the complicated environment to automatically make decisions on the direction to move. The device uses a consumer Red, Green, Blue and Depth (RGB-D) camera and an Inertial Measurement Unit (IMU) to detect obstacles. As the device leverages the ground height continuity among adjacent image frames, it is able to segment the ground from obstacles accurately and rapidly. Based on the detected ground,…
In the media, in policy-making, but also in research articles, algorithmic decision-making (ADM) systems are referred to as algorithms, artificial intelligence, and computer programs, amongst other terms. We hypothesize that such terminological differences can affect people's perceptions of properties of ADM systems, people's evaluations of systems in application contexts, and the replicability of research as findings may be influenced by terminological differences. In two studies (N = 397, N = 622), we show that terminology does indeed affect laypeople's perceptions of system properties (e.g.…
