The role of emotion in self-explanations by cognitive agents

Frank Kaptein, Joost Broekens, Koen Hindriks, Mark Neerincx

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Artificial Intelligence (AI) systems, including intelligent agents, are becoming increasingly complex. Explainable AI (XAI) is the capability of these systems to explain their behaviour, in a for humans understandable manner. Cognitive agents, a type of intelligent agents, typically explain their actions with their beliefs and desires. However, humans also take into account their own and other's emotions in their explanations, and humans explain their emotions. We refer to using emotions in XAI as Emotion-aware eXplainable Artificial Intelligence (EXAI). Although EXAI should also include awareness of the other's emotions, in this work we focus on how the simulation of emotions in cognitive agents can help them self-explain their behaviour. We argue that emotions simulated based on cognitive appraisal theory enable (1) the explanation of these emotions, (2) using them as a heuristic to identify important beliefs and desires for the explanation, and (3) the use of emotion words in the explanations themselves.

Original languageEnglish
Title of host publication2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages88-93
Number of pages6
Volume2018-January
ISBN (Electronic)9781538606803
DOIs
Publication statusPublished - 29 Jan 2018
Externally publishedYes
Event7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017 - San Antonio, United States
Duration: 23 Oct 201726 Oct 2017

Conference

Conference7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017
CountryUnited States
CitySan Antonio
Period23/10/1726/10/17

Fingerprint

Artificial intelligence
Intelligent agents

Cite this

Kaptein, F., Broekens, J., Hindriks, K., & Neerincx, M. (2018). The role of emotion in self-explanations by cognitive agents. In 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017 (Vol. 2018-January, pp. 88-93). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACIIW.2017.8272595
Kaptein, Frank ; Broekens, Joost ; Hindriks, Koen ; Neerincx, Mark. / The role of emotion in self-explanations by cognitive agents. 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 88-93
@inproceedings{e2a9c7b7299b4b93bfc84f9765d67d64,
title = "The role of emotion in self-explanations by cognitive agents",
abstract = "Artificial Intelligence (AI) systems, including intelligent agents, are becoming increasingly complex. Explainable AI (XAI) is the capability of these systems to explain their behaviour, in a for humans understandable manner. Cognitive agents, a type of intelligent agents, typically explain their actions with their beliefs and desires. However, humans also take into account their own and other's emotions in their explanations, and humans explain their emotions. We refer to using emotions in XAI as Emotion-aware eXplainable Artificial Intelligence (EXAI). Although EXAI should also include awareness of the other's emotions, in this work we focus on how the simulation of emotions in cognitive agents can help them self-explain their behaviour. We argue that emotions simulated based on cognitive appraisal theory enable (1) the explanation of these emotions, (2) using them as a heuristic to identify important beliefs and desires for the explanation, and (3) the use of emotion words in the explanations themselves.",
author = "Frank Kaptein and Joost Broekens and Koen Hindriks and Mark Neerincx",
year = "2018",
month = "1",
day = "29",
doi = "10.1109/ACIIW.2017.8272595",
language = "English",
volume = "2018-January",
pages = "88--93",
booktitle = "2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kaptein, F, Broekens, J, Hindriks, K & Neerincx, M 2018, The role of emotion in self-explanations by cognitive agents. in 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 88-93, 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017, San Antonio, United States, 23/10/17. https://doi.org/10.1109/ACIIW.2017.8272595

The role of emotion in self-explanations by cognitive agents. / Kaptein, Frank; Broekens, Joost; Hindriks, Koen; Neerincx, Mark.

2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 88-93.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - The role of emotion in self-explanations by cognitive agents

AU - Kaptein, Frank

AU - Broekens, Joost

AU - Hindriks, Koen

AU - Neerincx, Mark

PY - 2018/1/29

Y1 - 2018/1/29

N2 - Artificial Intelligence (AI) systems, including intelligent agents, are becoming increasingly complex. Explainable AI (XAI) is the capability of these systems to explain their behaviour, in a for humans understandable manner. Cognitive agents, a type of intelligent agents, typically explain their actions with their beliefs and desires. However, humans also take into account their own and other's emotions in their explanations, and humans explain their emotions. We refer to using emotions in XAI as Emotion-aware eXplainable Artificial Intelligence (EXAI). Although EXAI should also include awareness of the other's emotions, in this work we focus on how the simulation of emotions in cognitive agents can help them self-explain their behaviour. We argue that emotions simulated based on cognitive appraisal theory enable (1) the explanation of these emotions, (2) using them as a heuristic to identify important beliefs and desires for the explanation, and (3) the use of emotion words in the explanations themselves.

AB - Artificial Intelligence (AI) systems, including intelligent agents, are becoming increasingly complex. Explainable AI (XAI) is the capability of these systems to explain their behaviour, in a for humans understandable manner. Cognitive agents, a type of intelligent agents, typically explain their actions with their beliefs and desires. However, humans also take into account their own and other's emotions in their explanations, and humans explain their emotions. We refer to using emotions in XAI as Emotion-aware eXplainable Artificial Intelligence (EXAI). Although EXAI should also include awareness of the other's emotions, in this work we focus on how the simulation of emotions in cognitive agents can help them self-explain their behaviour. We argue that emotions simulated based on cognitive appraisal theory enable (1) the explanation of these emotions, (2) using them as a heuristic to identify important beliefs and desires for the explanation, and (3) the use of emotion words in the explanations themselves.

UR - http://www.scopus.com/inward/record.url?scp=85047254861&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047254861&partnerID=8YFLogxK

U2 - 10.1109/ACIIW.2017.8272595

DO - 10.1109/ACIIW.2017.8272595

M3 - Conference contribution

VL - 2018-January

SP - 88

EP - 93

BT - 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kaptein F, Broekens J, Hindriks K, Neerincx M. The role of emotion in self-explanations by cognitive agents. In 2017 7th International Conference on Affective Computing and Intelligent Interaction Workshops and Demos, ACIIW 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 88-93 https://doi.org/10.1109/ACIIW.2017.8272595