An Experiment on University English Translation Teaching Model Based on Big Data-Driven Learning

Abstract

Abstract Exploring the teaching mode of English translation in college to stimulate students’ learning initiative better and improve their English translation ability. In this paper, the basic principles of the plain Bayesian classification algorithm are introduced under big data technology-driven learning, and the conditional independence of plain Bayesian is illustrated. The algorithm and process of probabilistic classification of samples to be judged using great likelihood estimation are introduced, and the advantages and disadvantages of the algorithm are illustrated. Based on the disadvantages of this algorithm, the INB-MI classification algorithm is induced by adjusting the conditional probability after the number of smoothing using mutual information, and the validity is verified for this algorithm. For the university, English translation teaching was analyzed, a task-based English translation teaching model based on a blended environment was proposed, and the model was quantitatively analyzed with the INB-MI classification algorithm for the relevant data. In terms of cognitive types, the overall learning rate of this teaching model was 43.11%, 41.21%, 40.46%, and 38.3% for factual knowledge, conceptual knowledge, procedural knowledge, and metacognitive knowledge types, respectively. Regarding instructional evaluation, the percentage of those who agreed was 84.26%. Thus, the task-based English translation teaching model under big data-driven learning can help students integrate their existing knowledge and enhance their learning initiatives.