Analysis and Prediction of Students' Adaptation to Online Education Systems Based on Data Analysis and Decision Tree Machine Learning Algorithms

Abstract

In today's digital age, the popularity and development of online education systems provide students with more flexible and convenient ways of learning. However, students' adaptation to the online education system is affected by a variety of factors, including gender, age, educational background, and field of specialisation. Through in-depth analyses and studies of these factors, the following conclusions can be drawn: gender has little influence on students' adaptation to online education, and male and female students perform similarly overall, but the proportion of male students at high adaptation levels is significantly higher than that of females. The majority of students show medium adaptability, indicating that the overall effect of online education is average. students in the age groups of 6-10, 16-20 and 26-30 years old have lower adaptability levels, and there are more low adaptability groups among students in colleges and universities. students majoring in IT are more adapted to the online education system, and students not majoring in IT have relatively poorer adaptability level. Local students are more adaptable to online education than foreign students. In areas with unstable electricity, students' adaptability is usually lower. The decision tree algorithm predictions showed good overall model accuracy, with higher prediction accuracy for students with high, low and medium levels of adaptability. The test set accuracy was 93.27%, and the precision and recall were both 93.33%, indicating excellent model predictions. In summary, by deeply analysing the influence of various factors on students' adaptation degree to online education and using the random forest algorithm to make predictions, it can provide an important reference for improving the effectiveness of online education systems and provide useful insights for personalised education.