Abstract:
This research presents a training topic classification by Naïve Bayes Technique. Herein, the free simulation tool, WEKA is employed to simulate the classification processes. Firstly, the training topics data is separated to training data and test data. The training data is used to build the classification model, and later the created model is evaluated by the test data. In this work, the training topics data is collected from the faculty of Scinence, Chandrakasem Rajabhat University, from 1 October 2014 to 30 September 2016. It contains 273 cases.
To evaluate the created model, the training data with 70% and 30% of test data is applied to demonstrate its performance. The results showed that its classification accuracy was 80.95% with 0.2484 of RMSE. To compare results of classification, five experts grouped the training topics compared to the created model. The results presented the classification acceptance was 84%.