The present study tries to examine what kind of emotional responses human subjects express while interacting with an artificial agent if they believe that this agent is able to understand their emotional states. For this purpose different kind of computer games were programmed to elicit specific emotional appraisals. 30 subjects were asked to use the computer where an avatar provided a simulated intelligent feedback (experimental condition), or it only guided the subject across the different tasks (control). Multimodal synchronized data were captured: physiological data, posture, facial expressions, vocal behavior. All observational data were codified frame by frame using The Observer 5.0. THEME Software was used for the detection of recurrent patterns. This is an inprogress study: the paper includes initial results of the analysis of non-verbal communicative signals.
Ciceri, M. R., Balzarotti, S., Colombo, P., Analysis of the human multimodal emotional signals to an interactive computer, in L.P.J.J. Noldu, L. N., F. Griec, F. G., L. W.S. Loijen, L. W. L., P. H. Zimmerma, P. H. Z. (ed.), Proceedings of Measuring Behavior 2005. 5th International Conference on Methods and Techniques in Behavioral Research, Noldus Information Technology, Wageningen 2005: 615- 616 [http://hdl.handle.net/10807/20954]
Analysis of the human multimodal emotional signals to an interactive computer
Ciceri, Maria Rita;Balzarotti, Stefania;
2005
Abstract
The present study tries to examine what kind of emotional responses human subjects express while interacting with an artificial agent if they believe that this agent is able to understand their emotional states. For this purpose different kind of computer games were programmed to elicit specific emotional appraisals. 30 subjects were asked to use the computer where an avatar provided a simulated intelligent feedback (experimental condition), or it only guided the subject across the different tasks (control). Multimodal synchronized data were captured: physiological data, posture, facial expressions, vocal behavior. All observational data were codified frame by frame using The Observer 5.0. THEME Software was used for the detection of recurrent patterns. This is an inprogress study: the paper includes initial results of the analysis of non-verbal communicative signals.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
