Laughter detecting model using wearable EEG meter for Japanese comedy content

This paper proposes the use of a simple electroencephalogram (EEG) meter to measure feedback from viewers of comedy content. We propose a system that is a statistical model based on the random forest algorithm that learns the feature value of 40-dimension signal using a non-invasive wearable measuring instrument of EEG signals. Our proposed model generated from the EEG of nine participants and obtained an accuracy rate of 86.5%.

[1]  Salvatore Sessa,et al.  Automatic discrimination of laughter using distributed sEMG , 2015, 2015 International Conference on Affective Computing and Intelligent Interaction (ACII).

[2]  H. Jasper.  Report of the committee on methods of clinical examination in electroencephalography , 1958 .

[3]  David A. van Leeuwen,et al.  Automatic discrimination between laughter and speech , 2007, Speech Commun..

[4]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[5]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.