Towards a Reliable Evaluation of Mixed-Initiative Systems

Mixed-Initiative approaches are being applied in different real world domains and many systems have been developed to address specific problems. Though several successful examples of such tools encourage the use of this solving paradigm, it is worth highlighting that research in mixed-initiative interaction is still at an early stage and many important issues ne ed to be addressed. In particular, while some work has been devoted to the design of working prototypes and to identify relevant features of the mixed-initiative interaction, littl e attention has been given to the problem of evaluating the approach as a whole and the diverse aspects involved. This work aims at highlighting the need for effective evaluation studies f or this class of tools and provides a methodological contribution in this direction. In particular it uses an experimental met hodology well known in psychology and human-computer interaction for the problem of understanding users’ attitude wit h respect to mixed-initiative problem solving and investigates the importance of explanation services as a means to foster users’ involvement in the problem solving.

[1]  Joe Marks,et al.  Human-Guided Simple Search , 2000, AAAI/IAAI.

[2]  E. Langer,et al.  Matters of mind: Mindfulness/mindlessness in perspective , 1992, Consciousness and Cognition.

[3]  J. Bresina,et al.  Mixed-Initiative Planning in MAPGEN: Capabilities and Shortcomings , 2005 .

[4]  C. Nass,et al.  Machines and Mindlessness , 2000 .

[5]  Gabriella Cortellessa,et al.  Using a scheduling domain ontology to compute user-oriented explanations , 2004 .

[6]  Roger C. Schank,et al.  Explanation: A First Pass. , 1984 .

[7]  Drew McDermott,et al.  Issues in the Development of Human-Computer Mixed Initiative Planning , 1994 .

[8]  Mabry Tyson,et al.  A Mixed-initiative Framework for Robust Plan Sketching , 2003, ICAPS.

[9]  Bowen Hui,et al.  What is Initiative? , 1998, User Modeling and User-Adapted Interaction.

[10]  William S. Havens,et al.  A Framework for Designing and Evaluating Mixed-Initiative Optimization Systems , 2005 .

[11]  B. Chandrasekaran,et al.  Deep versus compiled knowledge approaches to diagnostic problem-solving , 1999, Int. J. Hum. Comput. Stud..

[12]  D. Chalmers Consciousness and Cognition , 1990 .

[13]  Shirley Gregor,et al.  Explanations from knowledge-based systems and cooperative problem solving: an empirical study , 2001, Int. J. Hum. Comput. Stud..

[14]  James F. Allen,et al.  TRIPS: An Integrated Intelligent Problem-Solving Assistant , 1998, AAAI/IAAI.

[15]  Frederick Hayes-Roth,et al.  The state of knowledge-based systems , 1994, CACM.

[16]  Stephen F. Smith,et al.  Comirem: an intelligent form for resource management , 2005, IEEE Intelligent Systems.

[17]  G. Nigel Gilbert,et al.  Explanation and dialogue , 1989, The Knowledge Engineering Review.

[18]  Ari K. Jónsson,et al.  MAPGEN: Mixed-Initiative Planning and Scheduling for the Mars Exploration Rover Mission , 2004, IEEE Intell. Syst..

[19]  Narendra Jussien,et al.  User-friendly explanations for constraint programming , 2001, WLPE.

[20]  Donald R. Jones,et al.  The division of labor between human and computer in the presence of decision support system advice , 2002, Decis. Support Syst..

[21]  Alfred Kobsa,et al.  Computational Models of Mixed-Initiative Interaction , 2007, Springer Netherlands.

[22]  Christopher K. Riesbeck,et al.  Experience, Memory and Reasoning , 1986 .