VYTEDU-CW: Difficult Words as a Barrier in the Reading Comprehension of University Students

Abstract

We present VYTEDU-CW (Educational Videos and Texts - Complex Word) as a corpus in Spanish made up of university educational texts containing difficult words. In its construction process, it worked with students of the different careers that make up the University of Guayaquil (Ecuador); the students were selected according to the level of studies with respect to the content of the texts of the corpus, this with the purpose that the text is not very easy for students who are in higher grades. The work consisted in the recognition and labeling of the complex words contained in the different texts that make up the VYTEDU corpus. It should be noted that one of the difficulties in reading comprehension is complex words, which become a barrier especially for those with special cognitive abilities. This new corpus had its origin in the VYTEDU corpus, whose demonstration was made at the congress of the SEPLN (Murcia-Spain, 2017) and on which several experiments were carried out. Currently, VYTEDU-CW is being used to continue researching the Automatic Simplification of Spanish Texts in the field of Natural Language Processing. A sample of students was taken from the different faculties and from the results the corpus statistics were obtained. The objective of this work is to determine that difficult words in educational texts become one of the main problems in the reading comprehension in the day to day of university students.