Document Type : Original Article
Authors
1
Department of Information Technology, Faculty of Computers and information, Luxor University, Egypt
2
Faculty of Economics and Business, Complutense University of Madrid, Spain
3
Department of Computer Science, Faculty of Computers and information, Luxor University, Egypt
4
College of Computer Science, Nahda University, Beni Suef, Egypt
Abstract
There are many classifications of Hadith mainly: according to reliability and memory of hadith' narrators (sahih, hasan, maudu, da’if), and according to the sayings, actions or characteristics of the Prophet (saying, doing, reporting, describing), each Hadith contains three main parts: Sanad, Matn and Taraf. In this study we try to find the relationship between the different classifications of hadith using Association rule mining, part of speech (POS) and Chi-square techniques, based on the text and Sanad of hadith to build a model that is able to distinguish and categorize the hadith categories, using supervised learning. The experimental results showed that the relation (confidence) between saying & sahih is 79.99%, doing & hasan is 64.5%, reporting & da’if is 64.84, describing & maudu is 58.5%, and the best classifier has given high accuracy been Naïve bayes NB; it achieved higher accuracy reached up to 97.5 %, followed by the LinearSVC and K- Neighbors reached up to 96.5%.
Keywords
Main Subjects
)
View on SCiNiTO