Skip to main content
SpringerLink
Log in

Conversation analysis at work: detection of conflict in competitive discussions through semi-automatic turn-organization analysis

  • Research Report
  • Published:
Cognitive Processing Aims and scope Submit manuscript

Abstract

This study proposes a semi-automatic approach aimed at detecting conflict in conversations. The approach is based on statistical techniques capable of identifying turn-organization regularities associated with conflict. The only manual step of the process is the segmentation of the conversations into turns (time intervals during which only one person talks) and overlapping speech segments (time intervals during which several persons talk at the same time). The rest of the process takes place automatically and the results show that conflictual exchanges can be detected with Precision and Recall around 70% (the experiments have been performed over 6 h of political debates). The approach brings two main benefits: the first is the possibility of analyzing potentially large amounts of conversational data with a limited effort, the second is that the model parameters provide indications on what turn-regularities are most likely to account for the presence of conflict.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Notes

  1. A first-order ergodic Markov model captures stochastic processes described by a set of N states S t  ∈ {1, …,  N}, that occur following a transition probability P(S t |S t-1). It is formally defined as a couple λ =  < A, π > . A is the N × N time-invariant transition probability matrix. The initial state probability distribution π = {π i } represents the probability of the first state π i  = P(S 1 = i). The parameters of a Markov chain can be easily estimated by frequency counts directly from training state sequences.

  2. Using only one sequence to train a model, the initial probability parameter array is meaningless.

References

  1. Allwood J (1992) The academic seminar as an arena of conflict and conflict resolution. Gothenbg Pap Theor Linguist 67:1–35

    Google Scholar 

  2. Allwood J (2007) Cooperation, competition, conflict and communication. Gothenbg Pap Theor Linguist 94:1–14

    Google Scholar 

  3. Asavathiratham C (2000) A tractable representation for the dynamics of networked Markov chain. PhD thesis, Department of ECS, MIT

  4. Bakeman R, Gottman J (1986) Observing interaction. Cambridge University Press, New York

    Google Scholar 

  5. Basu S, Choudhury T, Clarkson B, Pentland A (2001) Learning human interaction with the influence model. Technical Report 539, MIT MediaLab

  6. Bilmes J (1988) The concept of preference in conversation analysis. Lang Soc 17(2):161–181

    Article  Google Scholar 

  7. Bishop C, Tipping M (1998) A hierarchical latent variable model for data visualization. IEEE Trans Pattern Anal Mach Intell 20(3):281–293

    Article  Google Scholar 

  8. Bousmalis K, Mehu M, Pantic M (2009) Spotting agreement and disagreement: a survey of nonverbal audiovisual cues and tools. In: Proceedings of the international conference on affective computing and intelligent interaction, vol II. pp 121–129

  9. Brenneis D (1998) Language and dispute. Annu Rev Anthropol 17:221–237

    Article  Google Scholar 

  10. Cooper V (1986) Participant and observer attribution of affect in interpersonal conflict: an examination of noncontent verbal behavior. J Nonverbal Behav 10(2):134–144

    Article  Google Scholar 

  11. Cristani M, Pesarin A, Drioli C, Tavano A, Perina A, Murino V (2011) Generative modeling and classification of dialogs by a low-level turn-taking feature. Pattern Recogn 44(8):1785–1800

    Article  Google Scholar 

  12. Curhan J, Pentland A (2007) Thin slices of negotiation: predicting outcomes from conversational dynamics within the first five minutes. J Appl Psychol 92(3):802–811

    Article  PubMed  Google Scholar 

  13. Duda R, Hart P, Stork D (2001) Pattern classification. Wiley, New York

    Google Scholar 

  14. Duin R, Juszczak P, Paclek P, Pekalska E, De Ridder D, Tax D (2004) Prtools version 4.1: a matlab toolbox for pattern recognition. Internet http://www.prtools.org

  15. Fincham F, Beach S (1999) Conflict in marriage: implications for working with couples. Annu Rev Psychol 50:47–77

    Article  PubMed  CAS  Google Scholar 

  16. Fukunaga K (1990) Introduction to statistical pattern recognition. Academic Press, New York

    Google Scholar 

  17. Gottman J, Markman H, Notarius C (1977) The topography of marital conflict: a sequential analysis of verbal and nonverbal behavior. J Marriage Fam 39(3):461–477

    Article  Google Scholar 

  18. Jayagopi D, Hung H, Yeo C, Gatica-Perez D (2009) Modeling dominance in group conversations from non-verbal activity cues. IEEE Trans Audio Speech Lang Process 17(3):501–513

    Article  Google Scholar 

  19. Judd C (1978) Cognitive effects of attitude conflict resolution. J Conflict Resolut 22(3):483–498

    Article  Google Scholar 

  20. Kydd A (2010) Rationalist approaches to conflict prevention and resolution. Annu Rev Polit Sci 13:101–121

    Article  Google Scholar 

  21. Levine J, Moreland R (1998) Small groups. In: Gilbert D, Lindzey G (eds) The handbook of social psychology, vol 2. Oxford University Press, Oxford, pp 415–469

  22. Lissack T, Fu K (1976) Error estimation in pattern recognition via l-distance between posterior density functions. IEEE Trans Inf Theory 22(1):34–35

    Article  Google Scholar 

  23. Morrill C, Rudes D (2010) Conflict resolution in organizations. Annu Rev Law Soc Sci 6:627–651

    Article  Google Scholar 

  24. Oberschall A (1978) Theories of social conflict. Annu Rev Sociol 4:291–315

    Article  Google Scholar 

  25. Perina A, Cristani M, Castellani U, Murino V, Jojic N (2009) Free energy score space. In: Advances in neural information processing systems. pp 1428–1436

  26. Pesarin A, Calanca P, Murino V, Cristani M (2010) A generative score space for statistical dialog characterization in social signaling. In: Structural, syntactic, and statistical pattern recognition, Lecture Notes in Computer Science 6218. pp 630–639

  27. Pianesi F, Mana N, Cappelletti A, Lepri B, Zancanaro M (2008) Multimodal recognition of personality traits in social interactions. In: Proceedings of international conference on multimodal interfaces. pp 53–60

  28. Sacks H, Schegloff E, Jefferson G (1974) A simplest systematics for the organization of turn-taking for conversation. Language 50(4):696–735

    Article  Google Scholar 

  29. Salamin H, Favre S, Vinciarelli A (2009) Automatic role recognition in multiparty recordings: using social affiliation networks for feature extraction. IEEE Trans Multimedia 11(7):1373–1380

    Article  Google Scholar 

  30. Schegloff E (2000) Overlapping talk and the organisation of turn-taking for conversation. Lang Soc 29(1):1–63

    Article  Google Scholar 

  31. Sillars AL, Coletti SF, Parry D, Rogers MA (1982) Coding verbal conflict tactics: nonverbal and perceptual correlates of the “avoidance-distributive-integrative” distinction. Hum Commun Res 9(1):83–95

    Article  Google Scholar 

  32. Smith-Lovin L, Brody C (1989) Interruptions in group discussions: the effects of gender and group composition. Am Sociol Rev 54(3):424–435

    Article  Google Scholar 

  33. Tajfel H (1982) Social psychology of intergroup relations. Annu Rev Psychol 33:1–39

    Article  Google Scholar 

  34. Vinciarelli A (2007) Speakers role recognition in multiparty audio recordings using social network analysis and duration distribution modeling. IEEE Trans Multimedia 9(9):1215–1226

    Article  Google Scholar 

  35. Vinciarelli A (2009) Capturing order in social interactions. IEEE Signal Process Mag 26(5):133–137

    Article  Google Scholar 

  36. Vinciarelli A, Dielmann A, Favre S, Salamin H (2009) Canal9: a database of political debates for analysis of social interactions. In: Proceedings of IEEE workshop on social signal processing. pp 17–20

  37. Vinciarelli A, Pantic M, Bourlard H (2009) Social signal processing: survey of an emerging domain. Image Vis Comput 27(12):1743–1759

    Article  Google Scholar 

  38. Vinciarelli A, Pantic M, Heylen D, Pelachaud C, Poggi I, D’Errico F, Schröder M (2011) Bridging the gap between social animal and unsocial machine: a survey of social signal processing. IEEE Trans Affect Comput (to appear)

  39. Waxer P (1985) Video ethology: television as a data base for cross-cultural studies in nonverbal displays. J Nonverbal Behav 9(2):111–120

    Article  Google Scholar 

  40. Wharton T (2009) Pragmatics and nonverbal communication. Cambridge University Press, Cambridge

    Book  Google Scholar 

  41. Zhang D, Gatica-Perez D, Bengio S, McCowan I, Lathoud G (2006) Modeling individual and group actions in meetings with layered HMMs. IEEE Trans Multimedia 8(3):509–520

    Article  Google Scholar 

Download references

Acknowledgments

This work is partially supported by the European Communitys Seventh Framework Programme (FP7/2007-2013), under grant agreement no. 231287 (SSPNet).

Author information

Authors and Affiliations

  1. University of Verona, Verona, Italy

    Anna Pesarin, Marco Cristani & Vittorio Murino

  2. Italian Institute of Technology, Genoa, Italy

    Marco Cristani & Vittorio Murino

  3. University of Glasgow, Glasgow, UK

    Alessandro Vinciarelli

  4. Idiap Research Institute, Martigny, Switzerland

    Alessandro Vinciarelli

Authors
  1. Anna Pesarin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marco Cristani
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Vittorio Murino
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alessandro Vinciarelli
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Alessandro Vinciarelli.

Additional information

This article is part of the Supplement Issue on "Social Signals. From Theory to Applications," guest-edited by Isabella Poggi, Francesca D'Errico, and Alessandro Vinciarelli.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Pesarin, A., Cristani, M., Murino, V. et al. Conversation analysis at work: detection of conflict in competitive discussions through semi-automatic turn-organization analysis. Cogn Process 13 (Suppl 2), 533–540 (2012). https://doi.org/10.1007/s10339-011-0417-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10339-011-0417-9

Keywords

Search

Navigation