Stimuli and Experiment

Responsive image
Responsive image
15 Chinese film clips (positive, neutral and negative emotions) were chosen from the pool of materials as stimuli used in the experiments. The selection criteria for film clips are as follows: (a) the length of the whole experiment should not be too long in case it will make subjects fatigue; (b) the videos should be understood without explanation; and (c) the videos should elicit a single desired target emotion. The duration of each film clip is about 4 minutes. Each film clip is well edited to create coherent emotion eliciting and maximize emotional meanings. The details of the film clips used in the experiments are listed below:
Responsive image
There are totally 15 trials for each experiment. There is a 15s hint before each clips and 10s feedback after each clip. The order of presentation is arranged so that two film clips targeting the same emotion are not shown consecutively. For the feedback, participants are told to report their emotional reactions to each film clip by completing the questionnaire immediately after watching each clip. The detailed protocol is shown below:
Responsive image


Fifteen Chinese subjects (7 males and 8 females; MEAN: 23.27, STD: 2.37) participated in the experiments. In order to protect personal privacy, we have hidden their names and indicate each subject with a number from 1 to 15.

Dataset Summary

The SEED consists of two parts:

  1. In the "Preprocessed_EEG" folder, there are files containing downsampled, preprocessed and segmented versions of the EEG data in Matlab (.mat file). The data was downsampled to 200Hz. A bandpass frequency filter from 0-75Hz was applied. We extracted the EEG segments corresponding to the duration of each movie. There are totally 45 .mat (Matlab) files, one for per experiment. Each subject performed the experiment three times with an interval of about one week. Each subject file contains 16 arrays. 15 arrays contain segmented preprocessed EEG data of 15 trials in one experiment (eeg_1~eeg_15, channel√ódata). A array name labels contains the label of the corresponding emotional labels (-1 for negative, 0 for neutral and +1 for positive). The detailed order of the channels is included in the dataset. The EEG cap according to the international 10-20 system for 62 channels is shown below:
    Responsive image
  2. In the "Extracted_Features" folder, there are files containing extracted differential entropy (DE) features of the EEG signals, which was first proposed in [1]. These data is well-suited to those who want to quickly test a classification method without propcessing the raw EEG data. The file format is the same as the Data_prepocessed. We also computed differential asymmetry (DASM) and rational asymmetry (RASM) features as the differences and ratios between the DE features of 27 pairs of hemispheric asymmetry electrodes. All the features were further smooth with conventional moving average and linear dynamic systems (LDS) approaches. For more details about the feature extraction and feature smooth, please refer to [1] and [2].


Download SEED


If you feel the dataset helpful for your study, please add the following references to your publications.

1. Ruo-Nan Duan, Jia-Yi Zhu and Bao-Liang Lu, Differential Entropy Feature for EEG-based Emotion Classification, Proc. of the 6th International IEEE EMBS Conference on Neural Engineering (NER). 2013: 81-84. [link] [BibTex]

2. Wei-Long Zheng, and Bao-Liang Lu, Investigating Critical Frequency Bands and Channels for EEG-based Emotion Recognition with Deep Neural Networks, accepted by IEEE Transactions on Autonomous Mental Development (IEEE TAMD) 7(3): 162-175, 2015. [link] [BibTex]