Emotional Conversational Agents in Clinical Psychology and Psychiatry

  • María Lucila Morales-Rodríguez
  • Juan Javier González B.
  • Rogelio Florencia Juárez
  • Hector J. Fraire Huacuja
  • José A. Martínez Flores
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6437)

Abstract

This paper is based on a project at the University of Barcelona to develop the skills to diagnose the Generalized Anxiety Disorder (GAD) in students of psychology and psychiatry using a chatbot. The problem we address in this paper is to convert a chatbot in an emotional conversational agent capable of generating a believable and dynamic dialogue in natural language. For it, the dialogues convey traits of personality, emotions and its intensity. We propose to make an AIML language extension for the generation of believable dialogue, this extension will allow to create a more realistic scenario for the student to diagnose the condition simulated by the conversational agent. In order to measure the perception of the emotional state of the ECA expressed by the speech acts a survey was applied.

Keywords

Conversational Agent Personality Emotions Natural Language AIML 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Gutiérrez, J., Alsina, I., Rus, M., Pericot, I.: Virtual Agents for Teaching Diagnostic Skills in Clinical Psychology and Psychiatry. In: CGVR, Las Vegas Nevada, USA (2009)Google Scholar
  2. 2.
    Wallace, R.: Don’t Read Me - A.L.I.C.E. and AIML Documentation. Fecha de consulta 01 de Marzo del 2010 (2000), http://www.alicebot.org/documentation/dont.html
  3. 3.
    Morales-Rodriguez, M.L., Pavard, B., González-Barbosa, J.J.: Virtual Humans and Social Interaction. In: CGVR 2009, pp. 158–163 (2009)Google Scholar
  4. 4.
    Connie, T., Sing, G.O., Michael, G.K.O., Huat, K.L.: A Computational Approach to Emotion Recognition in Intelligent Agent. In: The Asian Technology Conference in Mathematics (ATCM 2002), Multimedia University, Malacca, December 17-21 (2002)Google Scholar
  5. 5.
    Huang, H., Cerekovic, A., Tarasenko, K., Levacic, V., Zoric, G., Pandzic, I., Nakano, Y., Nishida, T.: Integrating Embodied Conversational Agent Components with a Generic Framework. Published in International Journal of Multiagent and Grid Systems 4(4) (2008)Google Scholar
  6. 6.
    Kopp, S., Becker, C., Wachsmuth1, I.: The Virtual Human Max - Modeling Embodied Conversation. Artificial Intelligence Group, University of Bielefeld, P.O. Box 100131, 33501 Bielefeld, Germany (2006)Google Scholar
  7. 7.
    Ghasem-Aghaee, N., Khalesi, B., Kazemifard, M., Ören, T.I.: Anger and Aggressive Behavior in Agent Simulation. In: Summer Computer Simulation Conference (2009)Google Scholar
  8. 8.
    McCrae, R., John, O.: An Introduction to the Five-Factor Model and Its Applications. Journal of Personality 60, 175–215 (1992)CrossRefGoogle Scholar
  9. 9.
    Cerezo, E., Baldassarri, S., Cuartero, E., Serón, F.: Agentes virtuales 3D para el control de entornos inteligentes domóticos. Dept. de Ingeniería de Sistemas e Informática, Universidad de Zaragoza, Instituto de Investigación en Ingeniería de Aragón, I3A (2007)Google Scholar
  10. 10.
    Kshirsagar, S., Magnenat-Thalmann, N.: A multilayer personality model. In: Proceedings of the 2nd International Symposium on Smart Graphics, pp. 107–115. ACM, New York (2002)CrossRefGoogle Scholar
  11. 11.
    Morales-Rodriguez, M.L.: Modèle d’interaction sociale pour des agents conversationnels animés. Application à la rééducation de patients cerebro-lésés. PhD Tesis. Toulouse, Université Paul Sabatier, 108 p. (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • María Lucila Morales-Rodríguez
    • 1
  • Juan Javier González B.
    • 1
  • Rogelio Florencia Juárez
    • 1
  • Hector J. Fraire Huacuja
    • 1
  • José A. Martínez Flores
    • 1
  1. 1.División de Estudios de Posgrado e InvestigaciónInstituto Tecnológico de Ciudad MaderoCiudad MaderoMéxico

Personalised recommendations