Self-organizing maps for research evaluation of doctoral dissertations: The case of teaching Social Sciences in Spain

OLMEDO-MORENO, EVA M.; PASSONI, ISABEL; CURIEL-MARÍN, ELVIRA; FERNÁNDEZ-CANO, ANTONIO

RELIEVE - Revista Electronica de Investigacion y Evaluacion Educativa

Universidad de Valencia

Lugar: Valencia; Año: 2018 vol. 24 p. 1 - 20

This paper has as main objective to highlight the potential use of neural networks, self-organized maps type (SOM), as a clarifying tool in the treatment, analysis and visualization of scientometric data, specifically, in the case of the analysis of the Spanish doctoral theses in teaching Social Sciences, indexed in TESEO (Spanish national database of dissertations), and defended between 1976 and 2014. A census of 301 doctoral theses has been recovered, analyzed according to autonomous communities (Andalusia and Catalonia), five-year term groups, thematic categories and educational stages. In Andalusia, the production is highest in the five-year period 1986-1990 and 2001-2005. In Catalonia, the most productive five-year periods were 1991-1995, 1996-2000, 2001-2005 and 2006-2010. More agreement is needed in the nomenclature of the teaching Social Sciences area, as well as an update in the operation of the TESEO database. As a general conclusion, it can be inferred that the resulting SOM allow to update the understanding of the state of the art in the area based on the various variables considered. The potentiality of SOM as an exploratory approximation of multivariate data becomes evident.