Integrating Digital Health Concepts into Language Training for Biotechnology Education Using Data Mining Technology

Abstract

This study explores the integration of digital health concepts into biotechnology education by developing a data-driven English teaching model tailored for biotechnology students. A "digital health" English integrated teaching model is proposed, combining digital health knowledge with innovative pedagogical approaches to enhance health-related communication skills. Utilizing data mining technology, the study employs the decision tree C5.0 algorithm to preprocess English Grade 4 score datasets. Decision tree generation rules are derived to analyze and predict students' performance, offering insights into optimizing educational strategies. To address the discrete nature of decision tree algorithms, the synthesized CET-4 scores were discretized to construct an analysis model for predicting English Grade 4 test scores. Simulation results demonstrated that the model achieved a mean absolute error (MAE) of 0.7, with a prediction accuracy of 79.85%, validating its reliability. The experimental teaching model was implemented with college biotechnology students, revealing significant improvements in their performance. The mean English scores of the experimental group were 87.12 points, surpassing the control group's mean of 82.47 points. Additionally, students in the experimental group exhibited enhanced interest and initiative in their learning behaviors. This research demonstrates the potential of integrating digital health concepts with data mining technology to enhance English teaching in biotechnology education. By fostering improved communication skills and academic performance, this model provides a practical framework for equipping future biotechnology professionals with essential language competencies necessary for the global biotechnology landscape. Further studies could explore extending this approach to other specialized domains within life sciences education.