Zum Inhalt springen

Nur-Lesen-Fassung: Das Forschungsinformationssystem (FIS) ist aus Sicherheitsgründen vorübergehend durch diese Nur-Lesen-Fassung ersetzt. Alle öffentlichen Inhalte und Volltexte sind weiterhin abrufbar; Anmeldung, Bearbeitung, Einreichung und Statistiken stehen nicht zur Verfügung. Bei Fragen: fis@uni-bamberg.de

Start › Publikationen › Female, white, 27? : Bias Evaluation on Data and Algorithms for Affect Recognition in Faces

Publikation

Female, white, 27? : Bias Evaluation on Data and Algorithms for Affect Recognition in Faces

Pahl, Jaspar; Rieger, Ines; Möller, Anna; u. a. (2022): Female, white, 27? : Bias Evaluation on Data and Algorithms for Affect Recognition in Faces, in: Bamberg: Otto-Friedrich-Universität, S. 973–987.

Details

Fakultät/Lehrstuhl
Autorin(nen)/Autor(en)
Möller, Anna
Wittenberg, Thomas
Verlagsangabe
Otto-Friedrich-Universität : Bamberg
Erscheinungsjahr
2022
Quelle/Weitere Ausgabe
FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency : 2022 Proceeding / .- New York, NY, USA : Association for Computing Machinery, 2022, S. 973-987 - ISBN: 978-1-4503-9352-2
Jahr der Erstpublikation
2022
Sprache(n)
Englisch
Lizenz
URN
Abstract

Nowadays, Artificial Intelligence (AI) algorithms show a strong performance for many use cases, making them desirable for real-world scenarios where the algorithms provide high-impact decisions. However, one major drawback of AI algorithms is their susceptibility to bias and resulting unfairness. This has a huge influence for their application, as they have a higher failure rate for certain subgroups. In this paper, we focus on the field of affective computing and particularly on the detection of bias for facial expressions. Depending on the deployment scenario, bias in facial expression models can have a disadvantageous impact and it is therefore essential to evaluate the bias and limitations of the model. In order to analyze the metadata distribution in affective computing datasets, we annotate several benchmark training datasets, containing both Action Units and categorical emotions, with age, gender, ethnicity, glasses, and beards. We show that there is a significantly skewed distribution, particularly for ethnicity and age. Based on this metadata annotation, we evaluate two trained state-of-the-art affective computing algorithms. Our evaluation shows that the strongest bias is in age, with the best performance for persons under 34 and a sharp decrease for older persons. Furthermore, we see an ethnicity bias with varying direction depending on the algorithm, a slight gender bias and worse performance for facial parts occluded by glasses.

GND-Schlagwort(e)
Affective Computing; Mimik; Gefühlsausdruck; Kategoriale Daten; Annotation; Bias; Fairness <Informatik>; Datenerhebung; Evaluation
Freie Schlagwort(e)
affective computing
action units
categorical emotions
metadata post-annotation
bias
fairness
data evaluation,
algorithm evaluation
DDC-Klassifikation
004 Computer science
RVK-Klassifikation
ST 302
Dokumenttyp
Konferenzveröffentlichung
URI
Datum der Freischaltung
22.09.2022

Permalink: https://fis.uni-bamberg.de/handle/uniba/55613 · Daten als JSON · Zitieren: BibTeX · RIS

Datenstand: 15.11.2026

Eingeschränkter Lesezugriff: Anmeldung, Bearbeitung und Einreichung sind vorübergehend deaktiviert.