The role of emotion in self-explanations by cognitive agents

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.

[1]  Emiliano Lorini,et al.  A logic of emotions: from appraisal to coping , 2012, AAMAS.

[2]  P. Churchland.  Folk Psychology and the Explanation of Human Behavior , 1989 .

[3]  Christine Tappolet,et al.  Emotions and the intelligibility of akratic action , 2003 .

[4]  Etienne B. Roesch,et al.  A Blueprint for Affective Computing: A Sourcebook and Manual , 2010 .

[5]  K. Suzanne Barber,et al.  Comprehending agent software , 2005, AAMAS '05.

[6]  Sabine A. Döring.  Explaining Action by Emotion , 2003 .

[7]  Marc Cavazza,et al.  Character-Based Interactive Storytelling , 2002, IEEE Intell. Syst..

[8]  Anind K. Dey,et al.  Why and why not explanations improve the intelligibility of context-aware intelligent systems , 2009, CHI.

[9]  Joost Broekens,et al.  Formal models of appraisal: Theory, specification, and computational model , 2008, Cognitive Systems Research.

[10]  Glenn Taylor,et al.  Explaining Agent Behavior , 2010 .

[11]  Andrew Ortony,et al.  The Cognitive Structure of Emotions , 1988 .

[12]  F. Keil,et al.  Explanation and understanding , 2015 .

[13]  Dirk Heylen,et al.  The Virtual Storyteller: story creation by intelligent agents , 2003 .

[14]  B. Malle.  How the Mind Explains Behavior: Folk Explanations, Meaning, and Social Interaction , 2004 .

[15]  Paul O'Rorke,et al.  Explaining Emotions , 1994, Cogn. Sci..

[16]  H. Chad Lane,et al.  Building Explainable Artificial Intelligence Systems , 2006, AAAI.

[17]  Joost Broekens,et al.  Formalizing Cognitive Appraisal : From Theory to Computation , 2006 .

[18]  Koen V. Hindriks,et al.  CAAF: A Cognitive Affective Agent Programming Framework , 2016, IVA.

[19]  K. Scherer.  Appraisal considered as a process of multilevel sequential checking. , 2001 .

[20]  John-Jules Ch. Meyer,et al.  Guidelines for developing explainable cognitive models , 2010 .

[21]  John-Jules Ch. Meyer,et al.  Design and Evaluation of Explainable BDI Agents , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[22]  Arthur C. Graesser,et al.  AutoTutor: an intelligent tutoring system with mixed-initiative dialogue , 2005, IEEE Transactions on Education.

[23]  Koen V. Hindriks,et al.  Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults , 2017, 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN).

[24]  Tibor Bosse,et al.  Challenges in Computational Modeling of Affective Processes , 2013, IEEE Trans. Affect. Comput..

[25]  Ana Paiva,et al.  FAtiMA Modular: Towards an Agent Architecture with a Generic Appraisal Framework , 2014, Emotion Modeling.

[26]  Koen V. Hindriks,et al.  Do You Get It? User-Evaluated Explainable BDI Agents , 2010, MATES.

[27]  Michael van Lent,et al.  An Explainable Artificial Intelligence System for Small-unit Tactical Behavior , 2004, AAAI.

[28]  Eva Hudlicka,et al.  To feel or not to feel: The role of affect in human-computer interaction , 2003, Int. J. Hum. Comput. Stud..

[29]  Rainer Reisenzein,et al.  Emotions as metarepresentational states of mind: Naturalizing the belief–desire theory of emotion , 2009, Cognitive Systems Research.

[30]  B. Malle,et al.  How People Explain Behavior: A New Theoretical Framework , 1999, Personality and social psychology review : an official journal of the Society for Personality and Social Psychology, Inc.

[31]  P. Petta,et al.  Computational models of emotion , 2010 .

[32]  H. Chad Lane,et al.  Explainable Artificial Intelligence for Training and Tutoring , 2005, AIED.

[33]  Stacy Marsella,et al.  A domain-independent framework for modeling emotion , 2004, Cognitive Systems Research.

[34]  Frank E. Ritter,et al.  Designs for explaining intelligent agents , 2009, Int. J. Hum. Comput. Stud..

[35]  Alexandru Popescu,et al.  GAMYGDALA: An Emotion Engine for Games , 2014, IEEE Transactions on Affective Computing.