Title :
A new method for students´ learning achievement evaluation based on the eigenvector method
Author :
Chen, Shyi-Ming ; Li, Ting-Kuei
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ. of Sci. & Technol., Taipei, Taiwan
Abstract :
This paper presents a new method for students´ learning achievement evaluation based on the eigenvector method. The proposed method transforms the attributes “accuracy rate” and “time rate” into the “effect of accuracy rate” and the “effect of time rate”, respectively. Then, it generates the relative important degrees of the attributes “effect of accuracy rate”, “effect of time rate”, “importance” and “complexity” based on the eigenvector method, respectively. Then, it uses the correlation coefficients between the attribute vectors and the standard deviations of the elements in the attribute vectors to calculate the fitness degrees of the attributes. Then, it generates the weights of the attributes based on the relative important degrees of the attributes and the fitness degrees of the attributes. Then, it generates the important degrees of the questions according to the weights of the attributes and the relation matrix representing the relationships between the questions and the attributes. Based on the important degrees vector of the questions, the grade matrix and the accuracy rate matrix, it calculates the learning achievement index of each student having the same original total score for students´ learning achievement evaluation. The proposed method provides us a useful way for students´ learning achievement evaluation based on the eigenvector method.
Keywords :
computer science education; educational administrative data processing; eigenvalues and eigenfunctions; fuzzy set theory; eigenvector method; student learning achievement evaluation; Accuracy; Complexity theory; Correlation; Eigenvalues and eigenfunctions; Indexes; Tin; Transforms; Eigenvector method; Fuzzy sets; Learning achievement index; Membership functions; Students´ learning achievement evaluation;
Conference_Titel :
Machine Learning and Cybernetics (ICMLC), 2010 International Conference on
Conference_Location :
Qingdao
Print_ISBN :
978-1-4244-6526-2
DOI :
10.1109/ICMLC.2010.5580814