Classification students with learning disabilities using Naïve Bayes Classifier and Decision Tree
Nittaya Muangnak, Wannapa Pukdee, Thapani Hengsanunkun · Networked Computing and Advanced Information Management · 2010
The Objective of this study is to preliminarily classify the student with learning disabilities before diagnostic physician using two classification techniques, Naive Bayes Classifier and Decision Tree with Model C4.5. In manual classification, the students in the school are observed by teachers who relate in study and recorded the data with specific class of student, appear or disappear learning disabilities. In experimental classification following these processes, first is generating the model by using training data set, next is predicting by testing the model with testing data set without attribute class. As a result of the study, the Decision Tree classifier can classify the student with learning disabilities better than the Naive Bayes classifier, 96.15% and 94.23% respectively. Nevertheless, this study result fit for preliminary classification for school before transfer the students who appear learning disabilities to physician.