Research on the individualized teaching of Chinese in higher vocational colleges based on cloud computing

Abstract

Whether it is the development trend of education in the whole world or the quality education that is being comprehensively promoted in China, more and more attention is paid to the students’ leading position in the entire education process, respect for students’ differences, and the importance of students’ personality development. This paper uses a distributed cloud computing platform to construct a clustering algorithm based on K-means-CE to categorize language learner characteristics based on language learner characteristics combined with the Felder-Silverman style model. Then, the ItemCF algorithm of collaborative filtering recommendation is studied, and the combined similarity calculation method is proposed to deploy the recommendation algorithm to the Hadoop cloud computing platform to realize parallelized calculation and improve the efficiency of the personalization algorithm. The differences in learner types in the information input, information processing, learning attitude, and learning behavior input dimensions of the learning style analysis model constructed in the study will be expressed in the performance (P<0.05). The total cognitive load of the cloud computing-based personalized teaching group of higher vocational Language (M=65.26, SD=8.58) is lower than that of the conventional teaching group (M=66.23, SD=10.09). The personalized teaching method based on cloud computing is better than the conventional teaching in refining the learners’ knowledge structure. The learners’ achievement rate of the target learning level is higher, and the effect of the personalized teaching is more significant.

Keywords

• distributed cloud computing
• felder-silverman style model
• k-means-ce clustering algorithm
• itemcf algorithm
• language personalized teaching
• 97d80