Human emotion plays an important role in communication without language, and it also supports research on human behavior. In addition, electroencephalogram signals have been highly confirmed by researchers for reliability as well as ease of storage and recognition. So, the use of electroencephalogram to identify emotion signals are currently a relatively new field. Many researchers are targeting the key ideas in this research field such as signal preprocessing, feature extraction and algorithm optimization. In this paper, we aim to recognize emotion signals using Long Short Term Memory (LSTM) algorithms. Emotional signals dataset was taken from DEAP database of koelstra authors and associates to serve this research. The research will focus on accuracy and training time, and it will test different architectural types as well as the initials of LSTM. The obtained results show the 3-dimensional cubes's structure has better performance than the 2-dimensional cubes's structure. In addition, our research is also compared with other authors' studies to prove the effectiveness of the classification algorithm.
