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.
KeywordsReading comprehension Lexical complexity Metrics Free software
Our gratitude to the contribution that PhD Alfonso Ureña, director of the PhD program in Information and Communication Technologies of the UJA (University of Jaén) and PhD Arturo Montejo - Director of this research project gave us, and also our thanks to MSc. Rocío Anguita from the University of Granada for her contribution in the development and statistical application of this material.
- 1.Neira Martínez, A.C., Reyes Reyes, F.T., Riffo Ocares, B.E.: Academic experience and reading comprehension strategies in first-year university students. Lit. Linguist. 31, 221–244 (2015)Google Scholar
- 3.Blanco, A., Gutiérrez, C.: Readability of health web pages for patients and readers of the general population. Span. Mag. Publ. Health 76(4), 321–331 (2002)Google Scholar
- 4.Raúl Ordonñez, M.: https://revistas.ulima.edu.pe/index.php/Persona/article/view/691/665
- 5.Anula, A.: Readings adapted to the teaching of Spanish as L2: linguistic variables for determining the level of readability. The evaluation in learning and teaching Spanish as L2, pp. 162–170 (2008)Google Scholar
- 8.Štajner, S., Saggion, H.: Readability indices for automatic evaluation of text simplification systems: a feasibility study for spanish. In: Proceedings of the Sixth International Joint Conference on Natural Language Processing, pp. 374–382 (2013)Google Scholar
- 9.López-Anguita, R., Montejo-Ráez, A., Martínez-Santiago, F.J., Díaz-Galiano, M.C.: Legibility of the text, complexity metrics and the importance of words. Nat. Lang. Process. 61, 101–108 (2018)Google Scholar
- 10.Senter, R.J., Smith, E.A.: Automated readability index. Cincinnati Univ. OH (1967)Google Scholar
- 11.Rodríguez, S.: Extraction of information from emails using natural language processing techniques (2017)Google Scholar
- 12.Mesa, J.: Processing of natural language and its application in hotel services (2016)Google Scholar
- 13.Orquín, A., Rodríguez, K., Amable, A., Martín, R., Echarte, Á., Morera, D.C.: System for the pre-processing of texts for Natural Language Processing (2009)Google Scholar
- 14.De Jesús Torres, J.A.: Design of an educational software for the learning of language and literature in the punctuation marks of the first-year students of general unified baccalaureate morning section, parallel F of the technical institute superior technical center DM Quito, period 2016 (Bachelor’s thesis, Quito: UCE). http://www.dspace.uce.edu.ec/handle/25000/11181