Reading Comprehension in University Texts: The Metrics of Lexical Complexity in Corpus Analysis in Spanish

The article focuses on the practical field of the development and implementation of a software application developed for the automatic processing of eight metrics to calculate the lexical complexity in a corpus that contains the transcriptions of university educational videos in Spanish called VYTEDU, prepared by teachers from the University of Guayaquil, Ecuador. The obtained result allowed to demonstrate the different indexes of lexical complexity that the texts have in terms of the comprehensibility of their content. One of the main characteristics of the texts lies in the difference in size and content. It should be noted that although some texts had greater content, the index of lexical complexity was lower than other texts whose content was smaller in size. The diffusion of the software supposes the use of it as a tool to continue researching in the field of Natural Language Processing. The application developed using free software tools facilitated the use of libraries in the field of Natural Language Processing contributing to the analysis of the complexity of text comprehension, making this research a second step to build an automatic simplification tool for text in Spanish in the higher academic field that is proposed as future work, since the first step was the construction of the VYTEDU corpus together with its publication.