Human features recognition with CNM: An applied study concerning undergraduate students

In this paper we apply the Combinatorial Neural Model (CNM) to help scientists in Applied Social Sciences to understand a proactive agent in relation to the social environment. CNM is a hybrid neural network that represents an alternative to overcome the black box limitation of the Multilayer Perceptron by applying the neural network structure along with a symbolic processing. The model built comprises the recognition of patterns from a socioeconomic survey and from a set of written texts, and aims at understanding the student point of view about its role in the society. The self-perception of the young in relation to willingness for social proactivity was studied. Proactivity was taken as the possibility of transforming society from the perspective of social inequality. The whole process was driven under CRISP-DM guidelines. The model succeeded in identifying different rules that characterize non-proactive students. Results show that current approach is useful for subsidizing educators and managers of educational institutions in decision making with information on students’ profile.