Affective States in Software Programming: Classification of Individuals based on their Keystroke and Mouse Dynamics

Abstract

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.

Keystroke Dynamics Patterns While Writing Positive and Negative Opinions

“…The effectiveness of emotion recognition based on the analysis of keystroke dynamics may be improved if other input modalities are also taken into account. In [ 16 ], data collected via both keyboard and mouse are used to infer the boredom and frustrations of a tutoring system users achieving accuracies over 70%. Another example of combining keyboard and mouse data to predict the level of valence and arousal data was presented in [ 17 ].…”