Enhancing Academic Achievement in Computer Science Students: An Experimental Study on the Efficacy of Deep Learning Teaching Methods in Higher Vocational Education

Abstract

In the era of digital transformation, the integration of information technology into learning has posed challenges and opportunities. Navigating the global knowledge economy requires individuals to acquire skills facilitating adaptation to evolving economic and societal landscapes. Deep learning, recognized as pivotal for addressing real-world challenges and fostering adaptive capabilities, has garnered attention in educational research. This study investigates the effect of a deep learning teaching approach on the academic achievement of computer science students at a higher vocational institution. Employing an experimental research method with an experimental and control group, the study involved pre- and post-tests for first-grade computer science students. Results from a quasi-experimental analysis at a vocational college reveal that the implementation of deep learning teaching methods significantly enhanced both deep learning levels and academic performance in the experimental group, surpassing the outcomes of the control group under traditional teaching methods. Statistical analyses, including paired samples t-tests and independent samples t-tests, underscore the ineffectiveness of traditional teaching in fostering deep learning levels. The study provides robust evidence supporting the practical and substantial benefits of integrating deep learning methods into educational practices, emphasizing their potential for enhancing student outcomes.