Empirical Evidence Relating EEG Signal Duration to Emotion Classification Performance

In emotion recognition using EEG, it is not generally agreed upon how much time an EEG signal sequence must have in order to maximize precision and recall rates. To the best of our knowledge, there is not a systematic evaluation of effects on classifier performance related to EEG signal durations. The human factors related to attention decreasing and tiredness increasing have imposed difficulties to create EEG datasets containing a rich variation of signal samples. This paper proposes an experimental evaluation of three different EEG datasets (DEAP, MAHNOB, and STEED) each one mainly characterized by short, intermediate and long signal (or stimulus) durations. Statistical evaluation pointed out that for an EEG dataset to be well-suited for emotion recognition it should have two main characteristics: emotion stimulus data should be publicly available and evaluated by world-wide volunteers, and media stimulus should have duration long enough to affect the subjects. Our statistical analysis revealed that, at least for the considered datasets, signals with duration longer than 60 seconds allow better classification results. This work did not analyse the impact to humans of longer stimulus media.

Automated summary

There is disagreement on the optimal duration of EEG signal sequences for emotion recognition and challenges related to human factors in attention and fatigue. This study proposes an experimental evaluation of different EEG datasets with varying signal durations. Statistical analysis suggests that signals longer than 60 seconds may lead to better classification results for emotion recognition, but the impact of longer stimulus media on humans remains unexplored.