Integrating Deep Learning-Based Educational Technologies in Biotechnology Training: An Effectiveness Evaluation from a Hybrid Education Perspective

Licong Chen
Geely University of China, Faculty of foreign languages and cultures, Chengdu, China, 641423

DOI:https://doi.org/10.5912/jcb2240

Abstract:

This study explores the application of deep learning-based educational technologies in a hybrid learning environment, specifically tailored for non-English major college students engaged in biotechnology training programs. Utilizing a mixed-methods approach that combines both quantitative (pre- and post-tests, surveys) and qualitative (interviews, observations) data, the research aimed to provide a comprehensive evaluation of the effectiveness of these innovative learning tools. Thirty students participated in the study, with findings indicating a significant enhancement in their average TOEFL scores, moving from 78 in the pre-test to 89 in the post-test—an average gain of 11 points. Survey results from the participants (N=30) corroborate the positive reception of the hybrid learning model. Students notably appreciated the flexibility provided by asynchronous learning materials (n=21, M=4.2) and the tailored learning experiences facilitated by the deployment of deep learning tools (n=19, M=4.5). Moreover, the enhanced accessibility to diverse learning resources beyond traditional classroom settings (n=15, M=4.0) and the autonomy to manage their learning pace (n=13, M=3.8) were highly valued. Thematic analysis of qualitative data further revealed that students particularly benefited from the personalized and engaging educational experiences provided by the deep learning applications. The hybrid environment’s flexibility and access to extensive asynchronous materials were highly favoured, aligning with contemporary educational trends in biotechnology training. While the adaptive learning model and enhanced flexibility were positively received, some challenges related to student motivation and the limited scope of social interaction were noted. The findings underscore the potential of integrating advanced deep learning technologies in biotechnology education, suggesting a promising avenue for enhancing learner engagement and academic performance through personalized and flexible learning frameworks. This study not only supports the efficacy of hybrid educational models in biotechnological training but also highlights the commercial viability of deep learning tools in enhancing educational outcomes in this specialized field.