
Language: English
Is this system biased? – How users react to gender bias in an explainable AI system.
Because of its potential to make decision-making more efficient and reliable, artificial intelligence (AI) is increasingly supporting consequential human decisions. However, AI systems have been found to replicate and reinforce social stereotypes by enforcing biases against minorities, women and people of colour. In particular, AI systems have repeatedly been found to reinforce gender biases by favouring men over women.
One approach to mitigating the negative impact of gender bias is to increase the transparency of AI systems by providing explanations using novel Explainable Artificial Intelligence (XAI) methods. Explanations help increase user participation and can help users identify and reject biased decision recommendations from AI systems. However, there are several challenges to research from a user perspective in XAI. First, the developed explanatory XAI methods have not been sufficiently evaluated through studies with users. Therefore, it is unclear how users understand and use the explanations of these methods. Second, the impact that XAI explanations of a biased AI system might have on user perceptions such as trust is unclear.
With our research, we want to investigate how users evaluate XAI explanations and whether these explanations could help them to detect biases in AI systems. In particular, we are interested in investigating the trade-off between positive effects of increasing transparency through XAI explanations and negative effects of bias detection using XAI explanations.
The event will be held in English.
Guest: Since June 2018, Miguel Angel Meza Martinez has been conducting doctoral research at the Institute of Information Systems and Marketing (IISM) at the Karlsruhe Institute of Technology. His research focuses on Interactive Machine Learning and Explainable Artificial Intelligence (XAI). The overall goal of his research is to understand how AI systems can be better designed so that users can interact with the system to improve it. For this collaboration to be successful, AI systems need to be transparent in how they make decisions. For this reason, it is important to provide explanations to users. Designing more transparent AI systems strengthens users' trust in them and influences their acceptance in the long run.
Moderation: Sabine Faller is a research assistant in the department of museum communication at ZKM | Karlsruhe. Her focus is on the conception and implementation of workshops, projects and educational programs in the fields of media art, digital education and online learning – currently for the research project »Digitalization in Dialog – digilog@bw«.
- Organization / Institution
- ZKM | Center for Art and Media Karlsruhe
Accompanying program
-
- Thu, October 13, 20227 pm
- Shaping Digital Futures
-
Symposium
Medientheater
-
- Thu, September 29, 20226 pm
- Coping with memes
-
Workshop
Online
-
- Thu, August 18, 20226 pm
- #meetdigilog
-
Online
-
- Mon, July 25, 20226 pm
- #meetdigilog
-
Talk
Online
-
- Thu, June 30, 20226 pm
- #meetdigilog
-
Talk
Online
-
- Sun, June 19, 202211 am
- Busted! Tricks surveillance algorithms
-
Workshop
Online
-
- Thu, May 19, 20226 pm
- #meetdigilog
-
Talk
Online
-
- Wed, May 04, 20227 pm
- Wikipedia: Who writes his_tory?
-
Workshop
Online
-
- Wed, April 27, 20226 pm
- #meetdigilog
-
Talk
Online
-
- Thu, March 31, 20226 pm
- Talking about cancer online?
-
Talk
Online
-
- Thu, December 02, 20215.30 pm
- »Fake it till you make it« – Fake reviews on Jameda, Yelp and Co.
-
Talk
Online
-
- Mon, November 22, 2021
- LehrerInnenfortbildung
-
Workshop
Online
-
- Thu, November 18, 20215 pm
- »Alexa, explain the world to me!«
-
Talk
Online
-
- Mon, October 18, 2021
- LehrerInnenfortbildung
-
Workshop
Online
-
- Thu, October 14, 20215 pm
- Digiloglounge Digital
-
Online
-
- Thu, October 07, 20215.30 pm
- #meetdigilog
-
Talk
Online
-
- Thu, September 30, 20215 pm
- Digiloglounge Digital
-
Online
-
- Sat, September 25, 20214.30 pm
- TOTAL GAIA – Digital
-
Workshop
Online
-
- Thu, September 23, 20215.30 pm
- #meetdigilog
-
Talk
Online
-
- Wed, September 08, 202110 am
- Starke Bilder im Netz: Message mit Memes! – digilog@bw
-
Workshop
Online
-
- Thu, August 26, 20215.30 pm
- #meetdigilog
-
Talk
Online
-
- Sat, June 26, 20214 pm
- Trust me! – digilog@bw
-
Workshop
Online
-
- Thu, June 24, 20215 pm
- Digiloglounge Digital
-
Talk
Online
-
- Fri, June 18, 20214 pm
- Wellbeing at Home – digilog@bw
-
Workshop
Online
-
- Mon, June 14, 20216 pm
- Artivism on the net
-
Workshop
Online
-
- Sat, May 29, 20214 pm
- Feminism and Memes – digilog@bw
-
Workshop
Online
-
- Thu, May 27, 20215.30 pm
- #meetdigilog
-
Talk
Online
-
- Sat, May 22, 20213 pm
- Wellbeing at Home – digilog@bw
-
Workshop
Online
-
- Thu, May 20, 20215 pm
- Digiloglounge Digital
-
Online
-
- Mon, May 10, 20216 pm
- Artivism on the net
-
Workshop
Online
-
- Sat, April 17, 20214 pm
- Faking News Factory – digilog@bw
-
Workshop
Online
-
- Thu, April 15, 20215.30 pm
- #meetdigilog
-
Online
-
- Mon, April 12, 20216 pm
- Artivism on the net
-
Workshop
Online
-
- Thu, April 08, 20215 pm
- Digiloglounge Digital
-
Online
-
- Thu, March 25, 20215.30 pm
- #meetdigilog
-
Online
-
- Sat, March 20, 20214 pm
- Digital Feeling
-
Workshop
Online
-
- Thu, March 18, 20215 pm
- Digiloglounge Digital
-
Online
-
- Mon, March 08, 20216 pm
- Artivism on the net
-
Workshop
Online
-
- Thu, February 18, 20215 pm
- Digiloglounge Digital
-
Online
-
- Thu, January 28, 20215 pm
- Digiloglounge Digital
-
Online
-
- Thu, December 17, 20205 pm
- Digiloglounge Digital
-
Online
-
- Thu, November 19, 20205 pm
- Digiloglounge Digital
-
Online
-
- Thu, October 15, 20205 pm
- Digiloglounge Digital
-
Online
-
- Thu, September 17, 20205 pm
- Digilounge Digital
-
Online
-
- Wed, September 11, 20197 pm
- dialog@bw
-
Medientheater