Analysis And Research On Online Education Student Knowledge Level

As a new type of education,the online education brings a lot of convenience to people’s life and study.Through online education,people can learn knowledge at any time and at any place.They can not only share excellent education resources with others,but also save time and improve efficiency in studying.By analyzing the knowledge level of the online education students,we can assess the knowledge level of the students accurately,and provide guidance for improving the learning ability of the online education students.In this thesis,a more objective correlation analysis method of the online education students’ knowledge level is designed for the relevance analysis of the online education students’ knowledge level.The correlation coefficients between the online education students’ knowledge level and some other factors of the students’ data are calculated by the Pearson correlation coefficient algorithm,the Spearman rank correlation coefficient algorithm,the Kendall rank correlation coefficient algorithm,and the rapid computation of the maximal information coefficient algorithm.Then according to the values of the above correlation coefficients,the process of the correlation degree mapping is carried out.The final correlation degree result of the four algorithms is evaluated by the principle of majority voting priority and the mean assessment assistance.Lastly,these related factors that influence the knowledge level of the online education students are analyzed by the final correlation degree result.Furthermore,the experimental results show that the above designed correlation analysis method is more objective than the single correlation coefficient algorithm for the correlation analysis of students’ knowledge level.Moreover,we can show that the knowledge level of the online education students is related to the academic performance,the types of interactions in learning materials,the length of study time,the times of repetition for learning materials,and the highest education level of the students.However,it is not related to their gender,age,and disability.In order to predict the knowledge level more precisely,this thesis constructs three different prediction models for the knowledge level of the online education students.They are based the naive Bayes,the k-nearest neighbor method and neural networks.Then we design the experiments separately.By the comparison of the experimental results,it is easy to see that the prediction result of the neural network classification algorithm is obviously better than those of the naive Bayes classification algorithm and the k-nearest neighbor classification algorithm.Finally,by analyzing the research results of the online education students’ knowledge level,we provide some suggestions for teaching strategies,thus providing effective guidance for the improvement of the students’ knowledge level and playing a positive role in the development of the online education.