The need for an interaction cost model in adaptive interfaces

ABSTRACT

The development of intelligent assistants has largely benefited from the adoption of decision-theoretic (DT) approaches that enable an agent to reason and account for the uncertain nature of user behaviour in a complex software domain. At the same time, most intelligent assistants fail to consider the numerous factors relevant from a human-computer interaction perspective. While DT approaches offer a sound foundation for designing intelligent agents, these systems need to be equipped with an interaction cost model in order to reason the impact of how (static or adaptive) interaction is perceived by different users. In a DT framework, we formalize four common interaction factors --- information processing, savings, visual occlusion, and bloat. We empirically derive models for bloat and occlusion based on the results of two users experiments. These factors are incorporated in a simulated help assistant where decisions are modeled as a Markov decision process. Our simulation results reveal that our model can easily adapt to a wide range of user types with varying preferences.

REFERENCES

• 1: D. Albrecht, I. Zukerman, and A. Nicholson. Pre-sending Documents on the WWW: A Comparative Study. In Proc. of IJCAI, pp. 1274--1279, 1999.
• 2: J. Boger, P. Poupart, J. Hoey, C. Boutilier, G. Fernie, and A. Mihailidis. A decision-theoretic approach to task assistance for persons with dementia. In Proc. of IJCAI, pp. 1293--1299, 2005.
• 3: T. Bohnenberger and A. Jameson. When policies are better than plans: decision-theoretic planning of recommendation sequences. In Proc. of IUI, pp. 21--24, 2001.
• 4: C. Boutilier, T. Dean, and S. Hanks. Decision-theoretic planning: Structural assumptions and computational leverage. Journal of AI Research, 11:1--94, 1999.
• 5: S. Card, P. Moran, and A. Newell. Psychology of HCI. Hillsdale, NJ: Erlbaum, 1980.
• 6: C. Conati, A. Gertner, and K. VanLehn. Using Bayesian networks to manage uncertainty in student modeling. Journal of UMUAI, 12(4):371--417, 2002.
• 7: K. Gajos, M. Czerwinski, D. Tan, and D. Weld. Exploring the Design Space For Adaptive Graphical User Interfaces. In Proc. of AVI, pp. 201--208, 2006.
• 8: W. Hick. On the rate of gain of information. Journal of Experimental Psych., 4:11--36, 1952.
• 9: A. Hornof and D. Kieras. Cognitive modeling reveals menu search is both random and systematic. In Proc. of CHI, pp. 107--114, 1997.
• 10: E. Horvitz. Principles of mixed-initiative. In Proc. of CHI, pp. 159--166, 1999.
• 11: E. Horvitz, J. Breese, D. Heckerman, D. Hovel, and K. Rommelse. The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users. In Proc. of UAI, pp. 256--265, 1998.
• 12: B. Hui. A Survey of Interaction Phenomena. Technical report, Dept. of Computer Science, Univ. of Toronto, 2007.
• 13: B. Hui and C. Boutilier. Who's Asking for Help? A Bayesian Approach to Intelligent Assistance. In Proc. of IUI, pp. 186--193, 2006.
• 14: B. Hui, S. Liaskos, and J. Mylopoulos. Requirements Analysis for Customizable Software. In Proc. of RE, pp. 117--126, 2003.
• 15: R. Hyman. Stimulus information as a determinant of reaction time. Journal of Experimental Psych., 45: 188--196, 1953.
• 16: J. McGrenere, R. Baecker, and K. Booth. An evaluation of a multiple interface design solution for bloated software. In Proc. of CHI, pp. 163--170, 2002.
• 17: M. Puterman. Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley and Sons, NY, 1994.

INDEX TERMS

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

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence

Keywords:
bloat, information processing, interaction models and techniques, perceived savings, user interaction studies, visual occlusion