Evaluating the interaction with synthetic agents using attention and affect tracking

ABSTRACT

We motivate an approach to evaluating the utility of synthetic agents that is based on human physiology rather than questionnaires. The primary tool is an eye tracker that provides quantitative evidence of a user's focus of attention. The secondary tool is a signal encoder for skin conductance and heart rate in order to gain insight into the user's affective state. The salient feature of our evaluation strategy is that it allows us to measure important properties of the user's interaction experience on a moment-by-moment basis. We describe an empirical study in which we compare attending behavior and affect of participants watching the presentation of an apartment by three types of media: a synthetic agent, a text box, and speech only.

REFERENCES

• 1: Doris M. Dehn , Susanne van Mulken, The impact of animated interface agents: a review of empirical research, International Journal of Human-Computer Studies, v.52 n.1, p.1-22, Jan. 2000 [doi>10.1006/ijhc.1999.0325]
• 2: Pete Faraday , Alistair Sutcliffe, An empirical study of attending and comprehending multimedia presentations, Proceedings of the fourth ACM international conference on Multimedia, p.265-275, November 18-22, 1996, Boston, Massachusetts, United States [doi>10.1145/244130.244225]
• 3: H. Prendinger, S. Descamps, and M. Ishizuka. MPML: A markup language for controlling the behavior of life-like characters. Journal of Visual Languages and Computing, 15(2):183--203, 2004.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.1 Multimedia Information Systems

Additional Classification:
  H. Information Systems
  H.5 INFORMATION INTERFACES AND PRESENTATION (I.7)
      H.5.2 User Interfaces (D.2.2, H.1.2, I.3.6)

General Terms:
Human Factors

Keywords:
eye tracking, presentation, synthetic agents, user study