Colour plays an important role in web site design. The selection of effective chromatic combinations and the relation of colour to the perceived aesthetic and emotional value of a web site is the focus of this paper. The subject of the reported research has been to define a model through which to be able to associate colour combinations with specific desirable emotional and aesthetic values. The presented approach involves application of machine learning techniques on a rich data set collected during a number of empirical studies. The data obtained were used to train a Bayesian Belief Network which associated a simple chromatic model to perceived aesthetic and emotional dimensions. A set of tools that have been build in the process to support the methodological framework and ensure its reusability with minimal effort, are also described.