Emotion and mood recognition in response to video
This paper presents a subject-dependent homogenous emotion recognition method using electroencephalogram (EEG) signals in response to video contents, and a correlation between emotions and moods of subjects in resting state. In the recent years, there has been a trend towards recognizing emotions...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Rinton Press Inc.
2015
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/48698/ http://irep.iium.edu.my/48698/ http://irep.iium.edu.my/48698/1/Emotion_and_mood_recognition_in_response_to_video.pdf |
| Summary: | This paper presents a subject-dependent homogenous emotion recognition method using
electroencephalogram (EEG) signals in response to video contents, and a correlation between emotions
and moods of subjects in resting state. In the recent years, there has been a trend towards recognizing
emotions invoked from watching videos. Thus, in this study, two video clips with explicit emotional
contents from movies and online resources were used, and the EEG results were recorded from four
subjects as they watched these clips. The best accuracies of 60.71% for valence and 63.73% for arousal
were obtained using a Mel-frequency cepstral coefficients (MFCC) and multilayer perceptron (MLP). The
results show that MFCC and MLP techniques are applicable in emotion recognition. The result shows that
the mood can be recognized from opened eyes or closed eyes experiment of a subject. Furthermore, the
results demonstrated that a positive video content can stimulate a subject into being in positive emotional
state even when the subject was in bad mood. The emotional state in response to watching a video was
shown to be correlated with Self-Assessment Manikin analysis. |
|---|