Technology for Learning a Sign Language in an Educational Environment: A Machine Learning-Based Approach

Rojas J.T.; Jaimes N.C.; Bardales D.G.; Bayona-Oré S. · TEM Journal (2026) · DOI: 10.18421/tem152-63

Resumen

The integration of emerging technologies, particularly machine learning, into educational environments has opened new opportunities for inclusive learning. This study presents the design, implementation, and evaluation of a web-based sign language learning system powered by machine learning. Waterfall methodology was used to describe the development of web-based systems. The system is struetured around three core dimensions: Expression, communication, and comprehension. A preexperimental quantitative approach was employed with a sample of 145 primary school students in Lima, Peru. Data were colleeted using a validated Likert-scale questionnaire applied before and after the intervention. Statistical analysis using the Wilcoxon signed-rank test showed significant improvements across all dimensions. Specifically, the percentage of students who felt fully capable of expressing themselves in sign language rose from 2% to 49%, while similar gains were observed in communication and comprehension. These findings demonstrate the potential of machine learning-based tools to support foundational sign language learning in inclusive educational settings. The study contributes to the growing field of AI-enhanced education and highlights the importance of accessible technology for students with and without disabilities.

Instituciones: Universidad de Lima; Universidad Autónoma del Perú