A METHODOLOGICAL APPROACH TO LITERARY SELECTION FOR STUDENTS' CAPACITIES USING COMPUTATIONAL LINGUISTICS

Selecting literary works that align with students' intellectual capacities is essential in education but often proves to be a complex task. Traditional text selection methods can be subjective and labor-intensive, resulting in mismatches between the reading difficulty of texts and students' abilities. This paper introduces a methodological approach that leverages computational linguistics (CL) and Natural Language Processing (NLP) techniques to enhance the selection process. By utilizing algorithms such as cosine similarity, TF-IDF, and Word2Vec, literary works are analyzed for linguistic complexity and matched to students based on their intellectual profiles. The study follows a three-step methodology: assessing students' intellectual capacity, analyzing linguistic features of texts, and employing machine learning algorithms for optimal selection. The results indicate that this approach increases student engagement and improves reading comprehension, making the text-matching process more efficient and accurate. Ultimately, the findings highlight the potential of CL methods to foster personalized learning by providing students with intellectually stimulating texts.