Field Association words with Naive Bayes Classifier based Arabic document classification
Document classification aims to assign a document to one or more categories based on its contents. This paper suggests the use of Field association (FA) words algorithm with Naïve Bayes Classifier to the problem of document categorization of Arabic language Our experimental study shows that using FA algorithm with Naïve Bayes (NB) Classifier gives the ~ 79% average accuracy and, using compound FA words with NB classifier gives ~ 89% average accuracy of the training documents.
Keywords: Field association words; compound Field association words; Arabic Information retrieval; precision; recall; F-measure; Naïve Bayes theorem
Download Full-Text