Skip to main content
. 2020 May 3;10(5):278. doi: 10.3390/brainsci10050278

Figure 1.

Figure 1

This figure describes the stages of our research methodology. In the beginning, high valence high arousal (HVHA) and low valence high arousal (LVHA) short videos were displayed to the participants of the AMIGOS experiment (A) and their affective responses were recorded using the EEG modality (B). Then, the EEG recordings (C) were pre-processed (D), while (E) shows the experimental details. The construction of brain networks using iCOH (F) followed next and the extraction of features based on the network’s weights as well as on graph theoretical properties was performed. ReliefF (G) concluded on the 10 best features per trait, and was used three times; the first time, for sorting the features extracted during HVHA block of clips; the second time, for sorting the features extracted during LVHA block of clips; and one more time, for sorting all the aforementioned features together (BOTH). Finally, the classification stage (H) yields the presented prediction accuracy for each one of the five dimensions of personality (neuroticism (N): 83.8%, extraversion (E): 83.8%, openness (O): 73%, agreeableness (A): 86.5%, and conscientiousness (C): 83.8%). EEG, electroencephalographic; iCOH, imaginary part of coherence.