Exploring the Digital Impact of Big Data-Enhanced Flipped Classroom Instruction in University English

Abstract

English language teaching (ELT) flip classroom is different from the traditional English language instructional mode, and its student-centered instructional method brings great challenges to the assessment of learning results. There are many factors that affect the results of instructional assessment. The grading criteria are complex and it is difficult to give an appropriate mathematical model with analytical expressions, which are mostly nonlinear classification problems. This paper discusses the instructional mode and instructional effect of "flipped classroom" in university ELT driven by big data, establishes a mathematical model with genetic algorithm neural network (GA-NN) model structure, trains the neural network with expert samples, and uses the trained neural network for data processing, thus obtaining a good assessment result. Compared with the traditional ELT assessment system, the assessment accuracy of the assessment algorithm in this paper has increased by 25.47%, and all the training samples are close to the expert assessment results. Therefore, the student assessment model based on GA-NN is a reasonable and feasible assessment model. In the simulation results of cultivating university students' writing ability and reading ability in university ELT, the students' writing ability and reading ability are obviously improved after implementing digital flipped classroom teaching.