Abstract
The focus of explainable Artificial Intelligence (XAI)
is to provide users with explanations of automated decision-making
processes in order to facilitate trust between AI systems and users.
Moreover, it aims to empower users by helping them to under-
stand the reasoning mechanism of an AI system. Research in XAI,
however, mostly ignores the influence of user’s socio-cultural back-
ground on their explanation needs. In this paper, we advocate a novel
approach within XAI, which takes the socio-cultural background of
users into consideration. We build on social scientific research sug-
gesting that the socio-cultural background is constitutive of one’s
‘mental programming’ and thus influences perception of explana-
tions. We then outline a research agenda and challenges of more
socio-culturally aware XAI.
is to provide users with explanations of automated decision-making
processes in order to facilitate trust between AI systems and users.
Moreover, it aims to empower users by helping them to under-
stand the reasoning mechanism of an AI system. Research in XAI,
however, mostly ignores the influence of user’s socio-cultural back-
ground on their explanation needs. In this paper, we advocate a novel
approach within XAI, which takes the socio-cultural background of
users into consideration. We build on social scientific research sug-
gesting that the socio-cultural background is constitutive of one’s
‘mental programming’ and thus influences perception of explana-
tions. We then outline a research agenda and challenges of more
socio-culturally aware XAI.
Original language | English |
---|---|
Publication status | Published - 2020 |
Event | Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction - Duration: 7 Sept 2020 → … https://sites.google.com/view/dexahai-at-ecai2020/home |
Workshop
Workshop | Workshop on Dialogue, Explanation and Argumentation for Human-Agent Interaction |
---|---|
Abbreviated title | DEXAHAI |
Period | 7/09/2020 → … |
Internet address |
Keywords
- Explainable Artificial Intelligence, XAI, Socio-cultural dimensions, Understandability