EEG signal classification in usability experiments

The affective computing aims to detect emotional states during the interaction between the user and the machine allowing the use of this information in decision-making processes. EEG signals related to emotional states can be applied to the context of software usability providing more resources to the validation process and the identification of the degree of user satisfaction. This work aims to establish a relationship between EEG signals and the user opinion about the usability of some Facebook privacy features. Based on the assumption that there are variation in brain activity during the execution of tasks labeled as “easy” or “difficult”, a performance evaluation was done based on a Linear Discriminant Analysis (LDA) and Support Vector Machines (SVM) classifiers. The Mean Power Spectral Density, in 7 frequency bands, from 8 electrodes in F, C, P, and O areas were used as features. The classification rates showed a small advantage of the SVM when all the 28 variables were used. However, when the 13 variables pointed by the Mann-Whitney U test were used, LDA showed good discrimination capability. The electrodes in F and C areas, related with cognition and motor functions, rejected null hypothesis in almost all frequency bands during the execution of the tasks, showing that it is possible to recognize the studied emotional states. Despite the fact that this was a preliminary study, it showed the feasibility of using the EEG as a potential source of information to be added to software usability testing.