Repository logo
 

Toward Affective XAI: Facial Affect Analysis for Understanding Explainable Human-AI Interactions.

Accepted version
Peer-reviewed

Type

Conference Object

Change log

Authors

Guerdan, Luke 
Raymond, Alex 

Abstract

As machine learning approaches are increasingly used to augment human decision-making, eXplainable Artificial Intelligence (XAI) research has explored methods for communicating system behavior to humans. However, these approaches often fail to account for the affective responses of humans as they interact with explanations. Facial affect analysis, which examines human facial expressions of emotions, is one promising lens for understanding how users engage with explanations. Therefore, in this work, we aim to (1) identify which facial affect features are pronounced when people interact with XAI interfaces, and (2) develop a multitask feature embedding for linking facial affect signals with participants’ use of explanations. Our analyses and results show that the occurrence and values of facial AU1 and AU4, and Arousal are heightened when participants fail to use explanations effectively. This suggests that facial affect analysis should be incorporated into XAI to personalize explanations to individuals’ interaction styles and to adapt explanations based on the difficulty of the task performed.

Description

Keywords

Journal Title

ICCVW

Conference Name

The First International Workshop on Responsible Pattern Recognition and Machine Intelligence (Responsible PR&MI 2021)

Journal ISSN

Volume Title

Publisher

IEEE

Rights

All rights reserved
Sponsorship
Engineering and Physical Sciences Research Council (EP/R030782/1)
L3Harris ASV and the Royal Commission for the Exhibition of 1851