Journal on Multimodal User Interfaces

, Volume 3, Issue 1–2, pp 131–140 | Cite as

HMM modeling of user engagement in advice-giving dialogues

Original Paper

Abstract

This research aims at defining a real-time probabilistic model of user’s engagement in advice-giving dialogues. We propose an approach based on Hidden Markov Models (HMMs) to describe the differences in the dialogue pattern due to the different level of engagement experienced by the users. We train our HMM models on a corpus of natural dialogues with an Embodied Conversational Agent (ECA) in the domain of healthy-eating. The dialogues are coded in terms of Dialogue Acts associated to each system or user move. Results are quite encouraging: HMMs are a powerful formalism for describing the differences in the dialogue patterns, due to the different level of engagement of users and they can be successfully employed in real-time user’s engagement detection. Though, the HMM learning process shows a lack of robustness when using low-dimensional and skewed corpora. Therefore we plan a further validation of our approach with larger corpora in the near future.

Real-time computational models of engagement Embodied conversational agents Advice-giving Hidden Markov models User engagement 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Mazzotta I, De Rosis F, Carofiglio V (2007) PORTIA: A user-adapted persuasion system in the healthy eating domain. IEEE Intell Syst 22(6):42–51 CrossRefGoogle Scholar
  2. 2.
    Mazzotta I, Novielli N, Silvestri E, de Rosis F (2007) ‘O Francesca ma che sei grulla?’. Emotions and irony in persuasion dialogues. In: Procs of the 10th conference of AI*IA—Special track on ‘AI for expressive media’. AI*IA 2007: artificial intelligence and human-oriented computing, Rome. LNCS, vol 4733. Springer, Berlin, pp 602–613 CrossRefGoogle Scholar
  3. 3.
    Prochaska J, Di Clemente C, Norcross H (1992) In search of how people change: applications to addictive behavior. Am Psychol 47:1102–1114 CrossRefGoogle Scholar
  4. 4.
    Petty RE, Cacioppo JT (1986) The elaboration likelihood model of persuasion. In: Berkowitz L (ed) Advances in experimental social psychology, vol 19. Academic Press, New York, pp 123–205 Google Scholar
  5. 5.
    de Rosis F, Novielli N, Carofiglio V, De Carolis B (2006) User modeling and adaptation in health promotion dialogs with an animated character. J Biomed Inf 39(5):514–531 CrossRefGoogle Scholar
  6. 6.
    de Rosis F, Batliner A, Novielli N, Steidl S (2007) ‘You are soo cool Valentina!’ Recognizing social attitude in speech-based dialogues with an ECA. In: Procs of ACII 2007, Lisbon Google Scholar
  7. 7.
    Charniak E (1993) Statistical language learning. MIT Press, Cambridge Google Scholar
  8. 8.
    Picard RW (2003) Affective computing: challenges. Int J Human-Comput Stud 59(12):55–64 CrossRefGoogle Scholar
  9. 9.
    Batliner A, Steidl S, Hacker C, Noth E, Niemann E (2005) Private emotions vs social interaction: towards new dimensions in research on emotions. In: Carberry S, De Rosis F (eds) Procs of the workshop on adapting the interaction style to affective factors Google Scholar
  10. 10.
    Bosma W, Andre’ E (2004) Exploiting emotions to disambiguate dialogue acts. In: Proceedings of the international conference on intelligent user interfaces. Island of Madeira Google Scholar
  11. 11.
    Litman D, Forbes K, Silliman S (2003) Towards emotion prediction in spoken tutoring dialogues. In: Proceedings of HLT/NAACL Google Scholar
  12. 12.
    J Gill A, Oberlander J (2002) Taking care of the linguistic features of extraversion. In: Proceedings of the 24th annual conference of the cognitive science society Google Scholar
  13. 13.
    Bickmore T, Cassell J (2005) Social dialogue with embodied conversational agents. In: van Kuppevelt J, Dybkjaer L, Bernsen N (eds) Advances in natural, multimodal dialogue systems. Kluwer Academic, New York Google Scholar
  14. 14.
    Peters C, Pelachaud C, Mancini M, Bevacqua E (2005) Engagement capabilities for ECAs, workshop “Creating bonds with ECAs”. Fourth international joint conf. on autonomous agents & multi-agent systems Google Scholar
  15. 15.
    Bickmore T, Picard R (2005) Establishing and maintaining long-term human-computer relationships. ACM Trans Comput-Human Interact Google Scholar
  16. 16.
    Sidner C, Lee C (2003) An architecture for engagement in collaborative conversations between a robot and a human. MERL Technical Report, TR2003-12 Google Scholar
  17. 17.
    Sidner C, Lee C (2003) An architecture for engagement in collaborative conversations between a robot and a human. MERL Technical Report, TR2003-12 Google Scholar
  18. 18.
    Campbell N (2008) Multimodal processing of discourse information; the effect of synchrony. In: Procs of the 2008 second international symposium on universal communication, pp 12–15 Google Scholar
  19. 19.
    Yu C, Aoki PM, Woodruff A (2004) Detecting user engagement in everyday conversations. In: Procs of international conference on spoken language processing, pp 1329–1332 Google Scholar
  20. 20.
    Pentland A (2005) Socially aware computation and communication. Computer 38(3):33–40 CrossRefGoogle Scholar
  21. 21.
    Core MG, Moore JD, Zinn C (2003) The role of initiative in tutorial dialogue. In: Procs of 10th conference of the European chapter of the association for computational linguistics, Budapest, Hungary, April 2003 Google Scholar
  22. 22.
    Shah F (1997) Recognizing and responding to student plans in an intelligent tutoring system: CIRCSIM-Tutor. Ph.D. thesis, Illinois Institute of Technology Google Scholar
  23. 23.
    Linell P, Gustavsson L, Juvonen P (1988) Interactional dominance in dyadic communication: a presentation of initiative-response analysis. Linguistics 26:415–442 CrossRefGoogle Scholar
  24. 24.
    O’Brien HL, Toms EG, Kelloway EK, Kelley E Developing and evaluating a reliable measure of user engagement Google Scholar
  25. 25.
    Collins R (2004) Interaction ritual chains. Princeton University Press, Princeton Google Scholar
  26. 26.
    Said NS (2004) An engaging multimedia design model. In: Procs of the 2004 conference in interaction design and children Google Scholar
  27. 27.
    Smardon R (2004) Streetwise science: toward a theory of the code of the classroom. Mind Cult Act 11:201–223 CrossRefGoogle Scholar
  28. 28.
    Olitsky S (2007) Promoting student engagement in science: Interaction rituals and the pursuit of a community of practice. J Res Sci Teach 44(1):33–56 CrossRefGoogle Scholar
  29. 29.
    Woodruff A, Aoki PM (2004) Conversation analysis and the user experience. Digit Creat 15(4):232–238 CrossRefGoogle Scholar
  30. 30.
    Walton D (2006) Examination dialogue: an argumentation framework for critically questioning an expert opinion. J Pragmat 38:745–777 CrossRefGoogle Scholar
  31. 31.
    Martalo’ A, Novielli N, de Rosis F (2008) Attitude display in dialogue patterns. In: Proceedings of AISB’08, symposium on ‘affective language in human and machine’ Google Scholar
  32. 32.
    Whittaker S (2003) Theories and methods in mediated communication. In: Handbook of discourse processes, LEA, Mahwah, NJ Google Scholar
  33. 33.
    Rabiner LR (1989) A tutorial on hidden Markov models and selected applications in speech recognition. Proc IEEE 77(2):257–286 CrossRefGoogle Scholar
  34. 34.
    Levin E, Pieraccini R, Eckert W (1998) Using Markov decision process for learning dialogue strategies. In: Proceedings of the IEEE international conference on acoustic, speech and signal processing, vol 1, pp 201–204 Google Scholar
  35. 35.
    Stolcke A, Coccaro N, Bates R, Taylor P, Van Ess-Dykema C, Ries K, Shriberg E, Jurafsky D, Martin R, Meteer M (2000) Dialogue act modeling for automatic tagging and recognition of conversational speech. Comput Linguist 26:3 CrossRefMathSciNetGoogle Scholar
  36. 36.
    Twitchell DP, Adkins M, Nunamaker JF, Burgoon JK (2004) Using speech act theory to model conversations for automated classification and retrieval. In: Procs of the 9th international working conference on the language-action perspective on communication modelling Google Scholar
  37. 37.
    Soller A (2004) Computational modeling and analysis of knowledge sharing in collaborative distance learning. UMUAI 14(4):351–381 Google Scholar
  38. 38.
    Clarizio G, Mazzotta I, Novielli N, de Rosis F (2006) Social attitude towards a conversational character. In: Proceedings of the 15th IEEE international symposium on robot and human interactive communication. RO-MAN 2006. Hatfield, UK, pp 2–7 Google Scholar
  39. 39.
    Carletta J (1996) Assessing agreement on classification tasks. The Kappa statistics. Comput Linguist 22 Google Scholar
  40. 40.
    Levinson SE, Rabiner LR, Sondhi MM (1983) An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition. Bell Syst Tech J 62(4):1035–1074 MATHMathSciNetGoogle Scholar
  41. 41.
    Juang B-H, Rabiner LR (1985) A probabilistic distance measure for Hidden Markov models. ATT Tech J 64(2):391–408 MathSciNetGoogle Scholar
  42. 42.
    Carofiglio V, De Carolis B, Mazzotta I, Novielli N, Pizzutilo S (2009) Towards a socially intelligent ECA. In: Proceedings of CHItaly ’09, Roma, Italy, pp 99–106 Google Scholar
  43. 43.
    Novielli N, Strapparava C (2009) Towards unsupervised recognition of dialogue acts, proceedings of human language technologies: the 2009 annual conference of the North American chapter of the association for computational linguistics, companion volume: student research workshop and doctoral consortium, pp 84–89 Google Scholar
  44. 44.
    Carofiglio V, de Rosis F, Novielli N (2005) Dynamic user modeling in health promotion dialogs. In: Tao J, Tan T, Picard RW (eds) Affective computing and intelligent interaction, pp 723–730 Google Scholar
  45. 45.
    Carter N, Young D, Ferryman J (2006) A combined Bayesian Markovian approach for behaviour recognition. In: Procs of the 18th international conference on pattern recognition Google Scholar

Copyright information

© OpenInterface Association 2009

Authors and Affiliations

  1. 1.Department of InformaticsUniversity of BariBari (BA)Italy

Personalised recommendations