Title :
Comparison of Attribute Selection Methods for Web Texts Categorization
Author :
Saian, Rizauddin ; Ku-Mahamud, Ku Ruhana
Author_Institution :
Fakulti Sains Komputer dan Matematik, Univ. Teknol. MARA Perlis, Arau, Malaysia
Abstract :
This paper presents a study on the performance of attribute selection methods to be used with Ant-Miner algorithm for web text categorization. The new generated data set by each attribute selection method was classified with Ant-Miner to see the performance in terms of predictive accuracy and the number of rules generated. The results of classification were also compared to C4.5 algorithm.
Keywords :
Internet; data mining; pattern classification; text analysis; C4.5 algorithm; Web texts categorization; ant-miner algorithm; attribute selection methods; classification rules; Accuracy; Art; Computer networks; Data mining; Genetics; Information retrieval; Machine learning algorithms; Search methods; Text categorization; Web pages; attribute selection; classification; machine learning; web mining;
Conference_Titel :
Computer and Network Technology (ICCNT), 2010 Second International Conference on
Conference_Location :
Bangkok
Print_ISBN :
978-0-7695-4042-9
Electronic_ISBN :
978-1-4244-6962-8
DOI :
10.1109/ICCNT.2010.13
