As smart devices are becoming an integral part of our everyday interaction with our surroundings, it is becoming important for these devices to rise above their role as tools, and attain the role of personal assistants, able to decide on our behalf and allow us to offload some of the cognitive burden of everyday decision-making. Perhaps one of the simplest but important types of decision-making is that of expressing preferences among competing options. Although humans are typically quite efficient in expressing such preferences in particular contexts, they are often at a loss when they are asked to explicate the underlying preference model according to which they make these decisions.
The iCOP project seeks to design and develop processes that monitor human users and efficiently elicit the model according to which they make choices in certain domains, in a manner that offers guarantees on the performance of the elicited model in future situations. As part of this project we are developing appropriate visual interfaces that present the elicited model to the user in a way that the user can comprehend and correct what has been elicited, and be convinced that the smart device making decisions on the user’s behalf is doing so in a manner that is compatible with the user’s preferences.
Computational Cognition Lab, Open University of Cyprus
Project Website: http://cognition.ouc.ac.cy/loizos?get=Michael.etal_2013_CPNetsExperiments