Advancement Through Research
Emotion analytics applied in a business setting provide solutions to understand customer emotions or employee performance and carry out real-time AI analysis of the data. This is a smarter, much more unbiased alternative to such business tools as email surveys, mystery shoppers or “rate the service” buttons – practices that tend to be subjective and inconsistent and often fail to produce accurate and meaningful data. Many kinds of research are conducted to detect the emotion of a person by using different formats of data like speech, text, gesture and facial expressions. The problem with this data is that it will vary depending on the origin, culture, and nation. Because of this, it is difficult to detect human emotions more accurately. To solve this, our research makes use of electroencephalogram (EEG) signals that are directly collected from the brain. These signals not only ignore the external factors but also helps to detect real emotions arising from the brain. To conduct this research, a DEAP Dataset for emotion analysis using physiological signals is used. Firstly, the raw signal data is processed by removing the noise and converting the time series signal to statistical data. This statistical data is used to perform binary classification of four emotions valence, arousal, dominance, and liking. Various classifying techniques are examined to find the model that provides the best classification accuracy on this data. The experimental results show that Logistic Regression and Support Vector Machine are the best techniques for binary emotion classification with an accuracy of 69.25% and 70.35% respectively.
Emotion Analysis, EEG, Machine Learning, DEAP Dataset
