Neural longitudinal mapping of multidimensional performance profiles of Latin American universities

Abstract

Objective. To introduce an artificial intelligence method and to use it to analyze the evolution of the multidimensional performance profiles of the most prominent Latin American universities, according to the Times Higher Education Latin America University Rankings.
 Design/Methodology/Approach. To multidimensionally characterize universities' performance profiles, we use the rankings' sub-scores indicators, which quantify five dimensions of academic endeavor assessed by this ranking. To automatically compare and visually analyze performance profile's evolution our method uses an artificial neural network.
 Results/Discussion. The neurocomputational procedure allowed us to discover all the characteristic performance profiles of the 50 best ranked universities (20 institutional profiles in 2019), and to visualize, in a knowledge map, the universities' groups sharing similar profiles. Furthermore, the profile's evolution of this group of universities was analyzed, and visually displayed in a sequence of knowledge maps, covering the four years period 2016-2019. In general, these universities show a remarkable improvement in Teaching, Research and Citation scores during 2016-2019. The profiles diversity of the best ranked universities, and the predominance and homogenization process of Brazilian universities profiles are noteworthy.
 Conclusions. Performance profile characterization using multiple indicators is a matter of interest in diverse domains. However, visualization or comparison of multidimensional performance profiles is not an easy task for the human mind. Even more challenging is the visual analysis of multidimensional performance profiles evolution. The neuro-longitudinal technique introduced is a useful tool to analyze and visualize the evolution of multidimensional performance profiles.
 Originality/Value. The approach and techniques introduced in the paper have an important degree of generality and can be used to analyze other type of rankings or multidimensional data.