Static Socio-demographic and Individual Factors for Generating Explanations in XAI: Can they serve as a prior in DSS for adaptation of explanation strategies?

Current XAI research shows that explanations of AI need to be tailored to the individual explainee. We investigate whether XAI explanations can be successfully adapted to humans, when based on an appropriate static partner model representing relevant features. More specifically, we analyze the effects of static socio-demographic and individual factors on the advice-taking of different explanation strategies in a human-agent-interaction scenario. Results showed significant effects of the participant’s risk value, the mathematical self-assessment and the distance and direction of the advice to the first selection on advice-taking. Leveraging these results for an adaptation scheme, we train a classifier to predict a suitable explanation strategy based on all static features. We compare this classifier to results from a classifier working on dynamic features. Our results show that dynamic factors are as important as the static ones. Using static and dynamic factors increased the classifier’s accuracy, but the model showed overfitting and no generalization. Dividing the dataset by nationality yielded better generalization performance, indicating that nationality has an effect on predicting advice-taking. In addition, we propose an adapted measurement for advice-taking that considers the adaption beyond the given advice in advice-taking.