TY  - JOUR
T1  - Developing an Effective Automatic Web Pages Categorization Base on Ambiguity Weighting
AU - Chirawichitchai, Nivet 
JO  - Research Journal of Applied Sciences
VL  - 8
IS  - 4
SP  - 230
EP  - 234
PY  - 2013
DA  - 2001/08/19
SN  - 1815-932x
DO  - rjasci.2013.230.234
UR  - https://makhillpublications.co/view-article.php?doi=rjasci.2013.230.234
KW  - Web pages categorization
KW  -ambiguity weighting
KW  -algorithm gain
KW  -F-measure
KW  -Thailand
AB  - Web pages categorization is the process of automatically assigning predefined categories. Feature weighting which calculates feature (term) values in web pages is an important preprocessing technique in Web pages categorization. In this study, researchers proposed developing an effective automatic web pages categorization base on ambiguity weighting focusing on the comparison of various term weighting schemes. Researchers found ambiguity weighting most effective in the experiments with SVM, NB and DT algorithms. Researchers also discovered that the ambiguity weighting is suitable for combination with the information gain feature selection method. The ambiguity weighting with classification algorithms yielded the best performance with the F-measure over all algorithms. Based on the experiments, the classification algorithm with the information gain feature selection yielded the best performance with the F-measure of 99%.
ER  -