Abstract:We propose a machine learning method for recognizing modern Arabic poems based on the common poetic features of modern Arabic poetry. The poetic features include: rhyming, repetition, use of diacritics and punctuations, and text alignment. The method can classify text documents as poem or non-poem documents with a very high accuracy of 99.81%.

The paper deals with problems that imbalanced and overlapping datasets often en- counter. Performance indicators as accuracy, precision and recall of imbalanced data sets, both with and without overlapping, are discussed and compared with the same performance indicators of balanced datasets with overlapping. Three popular classification algorithms, namely, Decision Tree, KNN (k-Nearest Neighbors) and SVM (Support Vector Machines) classifiers are analyzed and compared.

No abstract

No abstract