Enhance Arabic Classifier Using Extraction and Water Cycle as Feature Selection

Represent human language in a computational technique called Natural language processing to extract the most important words which is called Natural language processing. The research into this extraction has evolved from the Bag of Words to N-gram to the Educated Text Stemmer as parts of a sentence in the Arabic language to extract nouns and verbs, where the verbs and nouns in the Arabic language play an important role in the differentiation of each class label in machine learning 'Arabic classifier'. These methods of extraction cannot be applied to the Qur'an. Arabic word-net as extraction has a problem with the number of words and their sense is not comprehensive. Therefore, the water cycle was employed as feature selection to reduce the unimportant words using K-Nearest Neighbor classifiers, based on our experiments the purpose of extraction outperforms other extractions, and the water cycle as feature selection reduces the number of words to keep an accuracy.