Automatic prediction of individual performance from "thin slices" of social behavior

ABSTRACT

This paper targets the automatic detection of individual performances in group tasks by means of short sequences, "thin slices", of nonverbal behavior. We designed our task as a classification one. We also investigated the relevance of social context in our task and the effectiveness of our feature selection.

REFERENCES

• 1: Ambady, N., and Rosenthal, R. 'thin slices' of expressive behaviors as predictors of interpersonal consequences: A meta-analysis. Psychological Bulletin, 111, pp. 256--274, 1992
• 2: Burges, C.J.C., A Tutorial on Support Vector Machines for Pattern Recognition. In Data Mining and Knowledge Discovery, Vol. 2, No. 2, pp. 121--167, 1998
• 3: Carrere, S., and Gottman, J.M. Predicting divorce among newlyweds from the first three minutes of a marital conflict discussion. Family Process, 38, pp. 293--30, 1998
• 4: Chippendale, P. Towards Automatic Body Language Annotation. Proceedings of FG2006 (IEEE), pp. 487--492, Southampton, UK, 2006
• 5: Curhan, J.R., and Pentland, A. 'thin slices' of Negotiation: predicting outcomes from conversational dynamics within the first 5 minutes. Journal of Applied Psychology, Vol. 92, No. 3, pp. 802--811, 2007
• 6: Guyon, I., and Elisseeff, A. An Introduction to Variable and Feature Selection. Journal of Machine Learning Research 3 (2003), pp. 1157--1182, 2003
• 7: Hall, J. W., and Watson, W. H. The Effects of a normative intervention on group decision-making performance. In Human Relations, 23(4), 299--317, 1970
• 8: Hecht, M.A., and LaFrance, M. How fast can I help you? Tone of voice and telephone operator efficiency in interactions. Journal of Applied Social Psychology, 25, pp. 2086--2098, 1995
• 9: Hsu, C.W., and Lin C.-J. A Comparison of Methods for Multi-Class Support Vector Machines. IEEE Transactions on Neural Networks, 13, pp. 415--425, 2002
• 10: Jayagopi, D.B., Ba. S., Odobez, J.M., and Gatica-Perez, D. Predicting Two Facets of Social Verticality in Meetings from Five-Minute Time Slices and Nonverbal Cues. In Proceedings of ICMI08, Chania, October 2008
• 11: Kressel U. Pairwise Classification and Support Vector Machines. In B. Scholkopf, C.J.C. Burges, and A.J. Smola (eds.) Advances in Kernel Methods -- Support Vector Learning. MIT Press, Cambridge, MA, 1999
• 12: Landwehr N., Hall M., and Frank E. Logistic Model Tree. In Machine Learning 59 (1--2) 161--205, 2005
• 13: Lepri, B., Mana., N., Cappelletti, A., Pianesi, F., and Zancanaro, M. Modeling Personality of Participants during Group Interaction. In Proceedings of UMAP09, Trento, Italy, 2009
• 14: Mana, N., Lepri, B., Chippendale, P., Cappelletti, A., Pianesi, F., Svaizer, P, and Zancanaro, M. Multimodal Corpus of Multi-Party Meetings for Automatic Social Behavior Analysis and Personality Traits Detection. In Proceedings of Workshop on Tagging, Mining and Retrieval of Human-Related Activity Information, at ICMI07, Nagoya, Japan, 2007
• 15: Pentland, A. Honest Signals: how they shape our world. MIT Press, 2008
• 16: Pianesi, F., Mana, N., Cappelletti, A., Lepri B., and Zancanaro, M. Multimodal Recognition of Personality Traits in Social Interactions. In Proceedings of ICMI08, Chania, Crete, Greece, 2008
• 17: Platt, J. Fast Training of Support Vector Machines using Sequential Minimal Optimization. Advances in Kernel Methods -- Support Vector Learning, B. Schoelkopf, C. Burges, and A. Smola, eds., MIT Press, 1998
• 18: Raducanu, B., Vitria, J., and Gatica-Perez, D. You are Fired! Nonverbal Role Analysis in Competitive Meetings. In Proceedings IEEE ICASSP09, Taiwan, April, 2009

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.3 Group and Organization Interfaces
          Subjects: Computer-supported cooperative work

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.3 Group and Organization Interfaces
          Subjects: Synchronous interaction

General Terms:
Algorithms, Experimentation, Human Factors, Measurement

Keywords:
intelligent environments, performance prediction, small group interaction, support vector machines