A Hybrid Framework for Personality Prediction based on Fuzzy Neural Networks and Deep Neural Networks

In general, humans are very complex organisms, and therefore, research on their various dimensions and aspects including personality has become an attractive subject of research works. With the advent of technology, the emergence of a new kind of communication in the context of social networks has also given a new form of social communication to the humans, and the recognition and categorization of people in this new space have become a hot topic of research that has been challenged by many researchers. In this paper, considering the Big Five personality characteristics of the individuals, first, a categorization of the related works is proposed, and then a hybrid framework based on the fuzzy neural networks (FNN) and the deep neural networks (DNN) is proposed, which improves the accuracy of personality recognition by combining different FNN-classifiers with DNN-classifier in a proposed two-stage decision fusion scheme. Finally, a simulation of the proposed approach is carried out. The suggested approach uses the structural features of a social networks analysis (SNA) along with a linguistic (LA) analysis feature extracted from the description of the activities of the individuals and comparison with the previous similar research works. The results obtained well-illustrate the performance improvement of the proposed framework up to 83.2% of the average accuracy of the personality dataset.