Authors:
Yan Xia
1
;
Jian Shu
2
;
Na Xu
3
and
Hui Feng
1
Affiliations:
1
Shanghai Education Evaluation Institute, China
;
2
Shanghai General Motor, China
;
3
Shanghai Municipal Education Examinations, China
Keyword(s):
Data Mining, Information Entropy, Information Gain Ratio, Decision Tree, Discipline Classification, Discipline Evaluation.
Related
Ontology
Subjects/Areas/Topics:
Assessment and Accreditation of Courses and Institutions
;
Computer-Supported Education
;
Learning/Teaching Methodologies and Assessment
;
Social Context and Learning Environments
Abstract:
Discipline evaluation is an important part in higher education evaluation. It plays a significant role in
discipline construction in universities and colleges. It is challenging how to use scientific discipline
evaluation to classify disciplines, such as advantageous disciplines and newly-emerging ones. This paper
proposes an algorithm of discipline decision tree classification based on weighted information gain ratio. It
determines evaluation attributes and creates decision tree according to weighted information gain ratio.
Discipline classification rules are deduced by decision tree. An automatic classification system is developed,
implementing the algorithm and analysing data from universities and colleges in Shanghai. Experimental
results show that our scheme can achieve about 83.33% accuracy in forecasts. It provides advice and
guidance for discipline evaluation, and establishes foundation for discipline development strategy.