In this paper, a method is presented for the classification of an individual into two affective states: boredom and frustration. To gather the necessary data, the individual interacts with an Intelligent Tutoring System focused on the teaching of programming languages. The method involves a classifier based on k-NN, and feature vectors generated by the preprocessing of keystroke dynamics and mouse dynamics data. Accurate results are achieved by determining relevant subsets of the initial feature set, using genetic algorithms. These subsets facilitate the training of the classifiers for each affective state.