TY  - JOUR
TI  - A Review of Classification Methods for Social Emotion Analysis
AU  - Selvapriya M 
AU  -  Dr.Maria Priscilla. G
JO  - International Journal of Scientific Research in Computer Science, Engineering and Information Technology
PB  - Technoscience Academy
DA  - 2018/04/30
PY  - 2018
DO  - https://doi.org/10.32628/IJSRCSEIT
UR  - https://ijsrcseit.com/CSEIT1833684
VL  - 3
IS  - 3
SP  - 1737	
EP  - 1750
AB  - Emotion classification has a broad range of applications. There are many application which uses Facial Expression to evaluate human nature, feelings, judgment, opinion. Recognizing Human Facial Expression is not a simple task because of some circumstances due to illumination, facial occlusions, face color/shape etc. Moreover, online comments are typically characterized by a sparse feature space, which makes the corresponding emotion classification tasks are very difficult. In our research work, social emotional classifications are classified through artificial neural network (ANN), deep learning and rich hybrid neural network (HNN) which will directly and indirectly used to recognize human expression in various conditions. This review also focuses on an up-to-date hybrid deep-learning approach combining a convolutional neural network (CNN) for the spatial features of an individual frame and long short-term memory (LSTM) for temporal features of consecutive frames. The analysed methodologies are implemented using Matlab. The experimental results show that the CNN model attained better classification accuracy compared than rich Hybrid Neural Network (HNN) and Artificial Neural Network (ANN) schemes. The performance evaluation conducted was proved that the each and every method has unique advantage and disadvantages among each other.