Application Research on Naive Bayesian Network Classifier in the Cognitive Diagnosis

• 1、Bozhou Normal College
• 2、JiangXi Normal University

Abstract：Classification is a basic task in data analysis and pattern recognition that requires the construction of a classifier, that is, a function that assigns a class label to instances described by a set of attributes. One of the most effective classifiers, in the sense that its perfect performance is competitive with state-of-the-art classifiers, is the so-called naive Bayesian classifier. Naive Bayesian Networks Classifier is one of the Bayesian Classifiers. Due to its simple structure and powerful reasoning ability in solving nondeterminant problems, Naive Bayesian Network Classifiers is attracting more and more attention of the researchers. Naive Bayesian Network Classifiers is applied to the classification of cognitive diagnosis in modern education measurement and some simulation experiments were done to test dichotomous and polytomous. The method of how to construct a Naive Bayesian Networks Classifier which is used to cognitive diagnosis is introduced. Four kinds of attribute hierarchies were separately used as the basis for the simulation. For each of the four attribute hierarchies, a sample of 5000 expected item response vectors was generated to approximate a normal distribution, Given that samples only consist of expected response patterns which are free from slips, the observed item response patterns were generated by randomly adding slips to each of the expected response patterns. In this study, the percentage of random errors was manipulated to 5％,10％ and 15％ of the total number of item response to examine whether the number of random errors has an impact on the accuracy of classification methods. Compared with the typical classification method of cognitive diagnosis under the same conditions, Naive Bayesian Classifier has an obvious advantage.

Keywords： Naive Bayesian Networks Classifier Cognitive Diagnosis Classify