Using explainability to help children understand Gender Bias in AI
Visualitza/Obre
Cita com:
hdl:2117/363820
Tipus de documentComunicació de congrés
Data publicació2021
EditorAssociation for Computing Machinery (ACM)
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Machine learning systems have become ubiquitous into our society. This has raised concerns about the potential discrimination that these systems might exert due to unconscious bias present in the data, for example regarding gender and race. Whilst this issue has been proposed as an essential subject to be included in the new AI curricula for schools, research has shown that it is a difficult topic to grasp by students. We propose an educational platform tailored to raise the awareness of gender bias in supervised learning, with the novelty of using Grad-CAM as an explainability technique that enables the classifier to visually explain its own predictions. Our study demonstrates that preadolescents (N=78, age 10-14) significantly improve their understanding of the concept of bias in terms of gender discrimination, increasing their ability to recognize biased predictions when they interact with the interpretable model, highlighting its suitability for educational programs.
Descripció
The final publication is available at ACM via http://dx.doi.org/10.1145/3459990.3460719
CitacióMelsión, G. [et al.]. Using explainability to help children understand Gender Bias in AI. A: Interaction Design and Children. "IDC'21: Interaction Design and Children: Athens, Greece: June 24 - 30, 2021: proceedings". New York: Association for Computing Machinery (ACM), 2021, p. 87-99. ISBN 978-1-4503-8452-0. DOI 10.1145/3459990.3460719.
ISBN978-1-4503-8452-0
Versió de l'editorhttps://dl.acm.org/doi/10.1145/3459990.3460719
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
3459990.3460719.pdf | 5,490Mb | Visualitza/Obre |