Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

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

Publication

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

Faculty/Chair
Faculty/Professorship
Author
Möller, Anna
Wittenberg, Thomas
Publisher Information
Otto-Friedrich-Universität : Bamberg
Year of publication
2022
Source/Other editions
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
Year of first publication
2022
Language
English
Licence
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 Keywords
Affective Computing; Mimik; Gefühlsausdruck; Kategoriale Daten; Annotation; Bias; Fairness <Informatik>; Datenerhebung; Evaluation
Keywords
affective computing
action units
categorical emotions
metadata post-annotation
bias
fairness
data evaluation,
algorithm evaluation
DDC Classification
004 Computer science
RVK Classification
ST 302
Type
Conferenceobject
URI
Activation date
2022-09-22

Permalink: https://fis.uni-bamberg.de/handle/uniba/55613 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-16

Restricted read-only access: login, editing and submission are temporarily disabled.