Key Issues in Interactive Problem Solving: An Empirical Investigation on Users Attitude
This paper explores the interaction between human and artificial problem solvers when interacting with an Intelligent Scheduling System. An experimental study is presented aimed at investigating the users’ attitude towards two alternative strategies for solving scheduling problems: automated and interactive. According to an automated strategy the responsibility of solving the problem is delegated to the artificial solver, while according to an interactive strategy human and automated solvers cooperate to achieve a problem solution.
Previous observations of end-users’ reactions to problem solving systems have shown that users are often skeptical toward artificial solver performance and prefer to keep the control of the problem solving process. The current study aims at understanding the role played by both the users’ expertise and the difficulty of the problem in choosing one of the two strategies. Results show that user expertise and task difficulty interact in influencing this choice.
A second aspect explored in the paper concerns the context in which the end-users rely on explanations to understand the solving process. Explanations are in fact expected to play an important role when artificial systems are used for cooperative and interactive problem solving. Results support the hypothesis that explanation services are more often called into play in case of problem solving failures.
- 2.Burstein, M., McDermott, D.: Issues in the development of human-computer mixed-initiative planning. In: Gorayska, B., Mey, J.L. (eds.) Cognitive Technology, pp. 285–303. Elsevier, Amsterdam (1996)Google Scholar
- 4.Cohen, R., Allaby, C., Cumbaa, C., Fitzgerald, M., Ho, K., Hui, B., Latulipe, C., Lu, F., Moussa, N., Pooley, D., Qian, A., Siddiqi, S.: What is initiative? In: Haller, S., McRoy, S., Kobsa, A. (eds.) Computational Models of Mixed-Initiative Interaction, pp. 171–212. Kluwer Academic Publishers, Dordrecht (1999)Google Scholar
- 5.Davis, R.: Application of Meta-Level Knowledge to the Construction, maintenance and Use of Large Knowledge bases. In: Davis, R., Lenat, D. (eds.) Knowledge-Based Systems in Artificial Intelligence. McGraw-Hill, Inc., New York (1982)Google Scholar
- 13.Lovett, M.C., Anderson, J.R.: Making heads or tails out of selecting problem-solving strategies. In: Moore, J.D., Lehman, J.F. (eds.) Proceedings of the Seventeenth Annual Conference of the Cognitive Science Society, Hillsdale, NJ, pp. 265–270. Erlbaum, Mahwah (1995)Google Scholar
- 15.Mao, J., Benbasat, I.: Exploring the use of explanations in knowledge-based systems: a process tracing analysis. Working Paper 96-MIS-002. Faculty of Commerce, University of British Columbia, Canada (1996)Google Scholar
- 17.Schank, R.C.: Explanation: A first pass. In: Kolodner, J.L., Riesbeck, C.K. (eds.) Experience, Memory and Reasoning, pp. 139–165. Erlbaum Associates, Hillsdale (1986)Google Scholar
- 18.Smith, S.F., Cortellessa, G., Hildum, D.W., Ohler, C.M.: Using a scheduling domain ontology to compute user-oriented explanations. In: Castillo, L., Borrajo, D., Salido, M.A., Oddi, A. (eds.) Planning, Scheduling, and Constraint Satisfaction: From Theory to Practice. IOS Press, Amsterdam (2005)Google Scholar
- 19.Smith, S.F., Hildum, D.W., Crimm, D.A.: Interactive Resource Management in the Comirem Planner. In: IJCAI 2003 Workshop on Mixed-Initiative Intelligent Systems, Acapulco Mexico (August 2003)Google Scholar
- 20.Tsang, E.P.K.: Foundation of Constraint Satisfaction. Academic Press, London (1993)Google Scholar