The evaluation of written texts is a task that considers mainly two aspects: the syntactic and the semantic. The first one focuses on the form of the text and the second one on the meaning. The manual implementation of this task implies an effort in time and resources, which can be reduced if part of the process is carried out automatically. According to the literature reviewed, there are different techniques for the automatic correction of texts, one of which is the linguistic, which focuses on syntactic, semantic and pragmatic elements. Thus, the ongoing research is oriented to the automatic evaluation of syntactic errors in texts written in Spanish, as a starting point to ensure coherence and cohesion in the composition of texts, which may result useful in the academic environment. In order to carry out this study, a set of texts of students of an academic program was collected and analyzed, to which techniques of natural language processing and machine learning were applied. Additionally, the manual correction to the content of the corpus was carried out in order to compare the results obtained by both methods; according to the above, it was established that there is correspondence between them, and for this reason it was concluded that the automatic method serves as support in the process of syntactic correction of a text written in Spanish.
Computational linguistics; text analysis; natural language processing; artificial intelligence; syntax