Services on Demand
Journal
Article
Indicators
Cited by SciELO
Related links
Similars in SciELO
Share
Revista Iberoamericana de Tecnología en Educación y Educación en Tecnología
Print version ISSN 1851-0086On-line version ISSN 1850-9959
Abstract
LANZARINI, Laura; CHARNELLI, Emilia; BALDINO, Guillermo and DIAZ, Javier. Selección de atributos representativos del avance académico de los alumnos universitarios usando técnicas de visualización: Un caso de estudio. Rev. iberoam. tecnol. educ. educ. tecnol. [online]. 2015, n.15, pp.42-50. ISSN 1851-0086.
Educational Data Mining collects the various methods that allow extracting novelty and useful information from large data volumes in educational contexts. This paper describes the process used to, through advanced visualization techniques, identify the most relevant characteristics in relation to student academic performance at the School of Computer Science of the National University of La Plata. This is the initial step that greatly affects the efficiency and efficacy of the methods that are used to model the information, since the results obtained improve when the dimension of the problem decreases. This in turn results in a clearer and simpler representation of the available information. To achieve this, we propose analyzing and applying, after a data pre-processing stage, various visualization methods for the attributes for the classes or expected responses. With this approach, we expect to develop a work methodology that offers results that can be easily used and interpreted. Its application to the information relating to regular and non-regular students at the UNLP allowed establishing interesting relationships in relation to student academic performance. This directly affects the reasons why students drop out from university.
Keywords : Educational data mining; Visualization; Education; Attribute selection; Academic performance.