[c100] E. Papachristos, N. Tselios, N. Avouris, Inferring relations between color and emotional dimensions of a web site using Bayesian Networks, Proc. Interact 2005, Rome, September 2005, Lecture Notes in Computer Science, Volume 3585, Sep 2005, Pages 1075 - 1078. (pdf)
In this paper, a novel methodology for selecting appropriate color scheme for a web site is presented. The methodology uses a machine learning algorithm for generating a network that relates the color model of a web site with the emotional values that are attributed to it by its users. The approach involves an empirical study to collect data, used to train the algorithm. A preliminary case study has been conducted to validate the applicability of the methodology. Description of the framework and a set of tools that were built to support the methodology is also included.