Influence of prior and task generated emotions on XAI explanation retention and understanding

TL;DR

This study explores how prior and task-related emotions influence users' retention and understanding of AI explanations, revealing that emotions can induce biases and affect comprehension during decision support interactions.

Contribution

It provides novel insights into the role of emotions in explanation processing, highlighting their impact on understanding and potential biases in AI-assisted decision-making.

Findings

Prior emotions do not affect explanation ratings but influence understanding of certain features.

Personal attitude-related features induce arousal and affect comprehension.

Arousal impacts understanding of emotionally salient variables.

Abstract

The explanation of AI results and how they are received by users is an increasingly active research field. However, there is a surprising lack of knowledge about how social factors such as emotions affect the process of explanation by a decision support system (DSS). While previous research has shown effects of emotions on DSS supported decision-making, it remains unknown in how far emotions affect cognitive processing during an explanation. In this study, we, therefore, investigated the influence of prior emotions and task-related arousal on the retention and understanding of explained feature relevance. To investigate the influence of prior emotions, we induced happiness and fear prior to the decision support interaction. Before emotion induction, user characteristics to assess their risk type were collected via a questionnaire. To identify emotional reactions to the explanations of the relevance of different features, we observed heart rate variability (HRV), facial expressions, and self-reported emotions of the explainee while observing and listening to the explanation and assessed their retention of the features as well as their influence on the outcome of the decision task. Results indicate that (1) task-unrelated prior emotions do not affected the ratantion but may affect the understanding of the relevance of certain features in the sense of an emotion-induced confirmation bias, (2) certain features related to personal attitudes yielded arousal in individual participants, (3) this arousal affected the understanding of these variables.