Dataset for article entitled "An empirical evaluation of methodologies used for emotion recognition via EEG signals"

The data is split into two parts according to the two experiments described within the article. The dataset includes movies and python codes for classifying emotions from experiment 1, and EEG and ERP measurements from experiment 2 along with associated code for analyzing those data.

Experiment 1 tests the validity of the SEED dataset collated by Zheng, Dong, & Lu (2014) and, subsequently, our own stimuli. The objective was to test whether previous literature using such datasets as the aformentioned dataset by Zheng et al. is purportedly classifying between emotions based on emotion-related signals of interest and/or non-emotional ‘noise’.

Experiment 2 used stimuli that have been well-validated within the psychological literature as reliably evoking specific embodiments of emotions within the viewer, namely the NimStim face and ADFES-BIV datasets with the objective of classifying a person's emotional status using EEG.

All data was processed and analyses run in MATLAB or Python. All datasets used are included within the folders accompanied by the MATLAB or Python scripts for collating separable matrices and running the action.