Enhancing Digital Health Education and Research Outcomes through Support Vector Machine Analysis: A Biotechnological Approach

Abstract

With globalization advancing rapidly, proficiency in English has become crucial in the digital health sector. This paper delves into the application of Support Vector Machine (SVM) algorithms for English language recognition, pivotal for enhancing educational methods in digital health. We explore the construction of SVM sequence kernel functions and their specific requisites, applying these principles to recognize and interpret English phonetics. Our approach involves a novel phonetic recognition model based on a trinity teaching strategy encompassing letters, phonemes, and phonetic symbols, tailored for university-level English education. Through an experimental setup in college English classes, we assessed the impact of this speech recognition model on students' learning interest and autonomy. Data were collected via pre and post-test scores, along with questionnaires and interviews. Analysis revealed significant improvements in listening scores, with average score increases of 0.15, 0.38, 0.45, and 0.51 across four types of listening test questions. Notably, post-test scores in the experimental group surpassed those in the control group in most cases, with a significant p-value of 0.041 indicating substantial differences. These findings suggest that employing an SVM-based language recognition model in university English teaching can effectively enhance listening comprehension, offering insights for integrating such technologies into digital health education.