Fairness Perceptions of Artificial Intelligence: A Review and Path Forward

Narayanan, Devesh; Nagpal, Mahak; McGuire, Jack; Schweitzer, Shane; Cremer, David De

doi:10.1080/10447318.2023.2210890

Cited by 13 publications

(7 citation statements)

References 212 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, there are also some prejudices due to the tendency of decision-making because the algorithm designer may choose shortcuts based on efficiency considerations and may also be affected by the values of his circle. This will lead to deviations in the development and design of AI systems [1][2][3][4]. We hope to design an efficient AI system with fairness but inadvertently introduce bias into the system.…”

Section: Summary and Discussionmentioning

confidence: 99%

“…However, sensitive features may be critical to the explicability of the AI model. In addition, sensitive features for AI may be hidden in other attributes, and the combination of non-sensitive features needs to be used to determine the value of sensitive features [7,40], which imposes new biases in applications [2,36]. This offers a baseline for computing AI fairness [20,39].…”

Section: Constraints On Precision Fairness 31 Inexplicability Of Ai A...mentioning

confidence: 99%

“…Social bias could be caused by statistically biased algorithms or by other objective factors [23][24][25]. More details of measurement bias, evaluation bias, content production bias, emergent bias, ranking bias and population bias, behavioral bias, temporal bias, linking bias, and presentation bias can be found in associated publications [2]. There are several other categories of biases.…”

Section: Unavoidable Biases In the Datasetsmentioning

confidence: 99%

“…With the development of AI, it has entered almost all spheres of our lives everywhere and the fairness of such algorithms and applications has drawn attention from many applications [1][2][3][4][5]. Methodologies for such studies and applications in design and other areas have been well-studied [6][7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

AI Fairness–From Machine Learning to Federated Learning

Patnaik,

Wang

2024

CMES

View full text Add to dashboard Cite

This article reviews the theory of fairness in AI-from machine learning to federated learning, where the constraints on precision AI fairness and perspective solutions are also discussed. For a reliable and quantitative evaluation of AI fairness, many associated concepts have been proposed, formulated and classified. However, the inexplicability of machine learning systems makes it almost impossible to include all necessary details in the modelling stage to ensure fairness. The privacy worries induce the data unfairness and hence, the biases in the datasets for evaluating AI fairness are unavoidable. The imbalance between algorithms' utility and humanization has further reinforced such worries. Even for federated learning systems, these constraints on precision AI fairness still exist. A perspective solution is to reconcile the federated learning processes and reduce biases and imbalances accordingly.

show abstract

Section: Summary and Discussionmentioning

confidence: 99%

Section: Constraints On Precision Fairness 31 Inexplicability Of Ai A...mentioning

confidence: 99%

Section: Unavoidable Biases In the Datasetsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AI Fairness–From Machine Learning to Federated Learning

Patnaik,

Wang

2024

CMES

View full text Add to dashboard Cite

show abstract

“…In addition, these reactions worsen when the human likeness of chatbots is very high, a phenomenon referred to as the uncanny valley 9 . After all, humans deeply value human interaction 10 and this is especially true when their own preferences and financial decisions are implicated, as is the case for service provision 11 . However, these negative effects do not emerge if customers are deceived into believing they are interacting with another human and not a chatbot 12 – 14 .…”

Section: Introductionmentioning

confidence: 99%

The reputational and ethical consequences of deceptive chatbot use

McGuire,

De Cremer,

Hesselbarth

et al. 2023

Sci Rep

Self Cite

View full text Add to dashboard Cite

The use of chatbots is becoming widespread as they offer significant economic opportunities. At the same time, however, customers seem to prefer interacting with human operators when making inquiries and as a result are not as cooperative with chatbots when their use is known. This specific situation creates an incentive for organizations to use chatbots without disclosing this to customers. Will this deceptive practice harm the reputation of the organization, and the employees who work for them? Across four experimental studies, we demonstrate that prospective customers, who interact with an organization using chatbots, perceive the organization to be less ethical if the organization does not disclose the information about the chatbot to their customers (Study 1). Moreover, employees that work for an organization which requires them to facilitate the deceptive use of a chatbot exhibit greater turnover intentions (Study 2) and receive worse job opportunities from recruiters in both a hypothetical experimental setting (Study 3) and from professional job recruiters in the field (Study 4). These results highlight that using chatbots deceptively has far reaching negative effects, which begin with the organization and ultimately impact their customers and the employees that work for them.

show abstract

Digitale Verantwortung

Recki,

Kroth,

Krauß

et al. 2024

Verbraucherinformatik

View full text Add to dashboard Cite

ZusammenfassungDie Verbreitung digitaler Systeme beeinflusst Entscheidungen, Gesetze, Verhalten und Werte in unserer Gesellschaft. Dies wirkt sich auf Konsumgewohnheiten, Marktbeziehungen, Machtverteilung, Privatsphäre und IT-Sicherheit aus. Damit einhergehende Veränderungen haben direkte Auswirkungen auf unser Leben, was im Bereich der Technikfolgenabschätzung bzw. der angewandten Informatik unter dem Stichwort ELSI diskutiert wird. Dieses Kapitel fokussiert auf entsprechende Fragestellungen bezüglich ethischer Auswirkungen. Insbesondere rückt Fairness im Kontext automatisierter Entscheidungen in den Fokus, da Verbraucher:innen diesen zunehmend ausgesetzt sind. Zudem wird im Rahmen der gestiegenen Besorgnis über ökologische Auswirkungen das Thema Nachhaltigkeit am Beispiel von „Sharing Economy“ und „Shared Mobility“ weiter vertieft.

show abstract

Fairness Perceptions of Artificial Intelligence: A Review and Path Forward

Cited by 13 publications

References 212 publications

AI Fairness–From Machine Learning to Federated Learning

AI Fairness–From Machine Learning to Federated Learning

The reputational and ethical consequences of deceptive chatbot use

Digitale Verantwortung

Contact Info

Product

Resources

About