Adapting Dialogue to User Emotion - A Wizard-of-Oz study for adaptation strategies

  • Gregor Bertrand
  • Florian Nothdurft
  • Wolfgang Minker
  • Harald Traue
  • Steffen Walter
Conference paper


In Spoken Language Dialogue Systems (SLDS) there is a growing trend to make the system act more human-like to render the dialogue more agreeable for the user. One of the methods to achieve these system qualities is to take into account the way that the user is feeling and to react appropriately. However, it is not clear what appropriate means in this context. What is the system to do when sensing a specific emotion? Is the appropriate reaction user-dependent? Situation-dependent? Context-dependent? Is the appropriate reaction dependent on the complex process of neurotransmitters circulating in the brain system of the user at the moment of the reaction? In order to address some of the questions above we conduct a Wizard-of- Oz study based on the findings of a preliminary study. We are collecting data about different kinds of users that are put in a cognitively demanding situation. We try to find out relations between different types of users and different types of system strategies that address their emotional state.


Dialogue Strategy Behavioral Inhibition System Psychological Tendency Emotion Regulation Questionnaire Speak Dialogue System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Abler B, Kessler H (2009) Emotion Regulation Questionnaire Eine deutsche Version des ERQ von Gross & John. Diagnostica 55(3):144–152CrossRefGoogle Scholar
  2. 2.
    Allen J, Byron DK, Dzikovska M, Ferguson G, Galescu L (2001) Towards Conversational Human-Computer Interaction. AI Mag 22(4):27–37Google Scholar
  3. 3.
    Allen J, Ferguson G, Blaylock N, Byron D, Chambers N, Dzikovska M, Galescu L, Swift M (2006) Chester: Towards a personal medication advisor. Journal of Biomedical Informatics 39(5):500 – 513, DOI doi: 10.1016/j.jbi.2006.02.004, URL http://www. 2/0cfa004f0673cb2b8573e2a186a15ae9, dialog Systems for Health CommunicationsGoogle Scholar
  4. 4.
    André E, Rehm M, Minker W, B¨uhler D (2004) Endowing Spoken Language Dialogue Systems with Emotional Intelligence. In: Tutorial and Research Workshop Affective Dialogue Systems, Irsee (Germany), pp 178–187, URL Research.DS/publications/2004ea01.html
  5. 5.
    Bernsen NO, Dybkjaer H, Dybkjaer L (1994) Wizard of oz prototyping: How and when? In: CCI Working Papers in Cognitive Science and HCIGoogle Scholar
  6. 6.
    Bertrand G, Nothdurft F,Walter S, Scheck A, Kessler H (2010) Towards Investigating Effective Affective Dialogue Strategies. In: International Conference on Language Resources and Evaluation (LREC), Valetta, MaltaGoogle Scholar
  7. 7.
    Borkenau P, Ostendorf F (1993) NEO-F¨unf-Faktoren Inventar (NEO-FFI); nach Costa und McCrae. HogrefeGoogle Scholar
  8. 8.
    Ehrenthal J, Dinger U, Lamla A, Funken B, Schauenburg H (2009) Evaluation der deutschsprachigen Version des Bindungsfragebogens [Experiences in Close Relationship - Revised]. Psychotherapie, Psychosomatik, Medizinische Psychologie 59:215–223CrossRefGoogle Scholar
  9. 9.
    Hone K (2006) Emphatic Agents to Reduce User Frustration: The Effects of Varying Agent Characteristics. Interacting With Computers 18:227–245CrossRefGoogle Scholar
  10. 10.
    Jaksic N, Branco P, Stephenson P, Encarnação LM (2006) The Effectiveness of Social Agents in Reducing User Frustration. In: CHI ’06: CHI ’06 extended abstracts on Human factors in computing systems, ACM, New York, NY, USA, pp 917–922, DOI 10.1145/1125451.1125629
  11. 11.
    Likert R (1932) A technique for the measurement of attitudes. Archives of Psychology 22:55Google Scholar
  12. 12.
    Oviatt S (1996) User-centered Modeling for Spoken Language and Multimodal Interfaces. Multimedia, IEEE 3(4):26 –35, DOI  10.1109/93.556458 CrossRefGoogle Scholar
  13. 13.
    Partala T, Surakka V (2004) The Effects of Affective Interventions in Human- Computer Interaction. Interacting with Computers 16(2):295 – 309, DOI DOI:  10.1016/j.intcom.2003.12.001 CrossRefGoogle Scholar
  14. 14.
    Pittermann J, Minker W, Pittermann A (2009) Handling Emotions in Human- Computer Dialogues. SpringerGoogle Scholar
  15. 15.
    Schmalt H, Sokolowski K, Langens T (2000) Das Multi-Motiv-Gitter zur Erfassung von Anschluss, Leistung und Macht-MMG [The Multi-Motive-Grid of Connection, Performance and Power]. SwetsGoogle Scholar
  16. 16.
    Schneider-Düker M, Kohler A (1988) Die Erfassung von Geschlechtsrollen. Ergebnisse zur deutschen Neukonstruktion des Bern Sex-Role Inventory [Assessment of Sex Roles: Results of the German Version of the Bern Sex-Role Inventory]. Diagnostica 34:256–270Google Scholar
  17. 17.
    Strobel A, Beauducel A, Debener S, Brocke B (2001) A German version of Carver and White’s BIS/BAS scales. Zeitschrift für Differentielle und Diagnostische Psychologie 22:216–227CrossRefGoogle Scholar
  18. 18.
    Tukey JW (1977) Explanatory data analysis, Addison-Wesley, chap BoxandWhisker Plots, pp 39–43Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2011

Authors and Affiliations

  • Gregor Bertrand
    • 1
  • Florian Nothdurft
    • 1
  • Wolfgang Minker
    • 1
  • Harald Traue
    • 2
  • Steffen Walter
    • 2
  1. 1.University of Ulm, Institute of Information TechnologyUlmGermany
  2. 2.Medical Psychology, University Clinic for Psychosomatic Medicine and PsychotherapyUlm UniversityUlmGermany

Personalised recommendations