Electroencephalography (EEG) -based emotion recognition is being widely applied because it measures electrical correlates directly from the brain rather than the indirect measurement of other physiological responses initiated by the brain. The recent development of non-invasive and portable EEG sensors makes it possible to use them in real-time applications. This dataset contains EEG data of 15 participants from two commercial EEG devices: Muse S headband and Neurosity Crown. The participants watched a total of 16 short videos which elicited emotions from the valence arousal domain. We developed a lightweight emotion classification pipeline from this dataset which could be used in real-time in the future. Moreover, the dataset is compatible with the state-of-art AMIGOS dataset, and the developed pipeline outperforms the classification results obtained from the AMIGOS dataset.

The description of the dataset can be found in the paper.